INDEX

Explanations

phrases related to government departments, especially in the context of health, human services, housing, and urban development

oai_token-act-pair · gpt-3.5-turbo

references to various government departments and their functions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

"]=>

-0.76

rely

-0.67

jad

-0.66

etimes

-0.65

fman

-0.64

GF

-0.63

ilogy

-0.62

KER

-0.62

aretz

-0.62

aeus

-0.61

POSITIVE LOGITS

 Instruction

0.84

ĳå£«

0.84

 Corrections

0.80

 Affairs

0.79

 Consolid

0.78

ertation

0.76

 Merrill

0.74

escription

0.72

afort

0.71

 Service

0.70

Activations Density 0.110%

phrases related to government departments, especially in the context of health, human services, housing, and urban development

references to various government departments and their functions

No Comments

No Known Activations