INDEX

Explanations

phrases related to operation or functioning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "operate" and its variations in different contexts

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

hus

-0.80

hon

-0.79

ildo

-0.73

Fey

-0.68

ilde

-0.67

uran

-0.66

panic

-0.66

ixed

-0.66

alon

-0.65

akura

-0.65

POSITIVE LOGITS

 operated

0.77

 withd

0.72

ATING

0.70

 operations

0.70

querade

0.70

 Procedures

0.69

 subsidiaries

0.68

 licences

0.68

aution

0.67

 operation

0.67

Activations Density 0.022%

phrases related to operation or functioning

instances of the word "operate" and its variations in different contexts

No Comments

No Known Activations