INDEX

Explanations

terms related to policies, procedures, and decision-makers in governmental or organizational settings

oai_token-act-pair · gpt-3.5-turbo

terms related to policy-making and procedures

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

owship

-0.84

culus

-0.75

 Syndrome

-0.72

usercontent

-0.72

ipel

-0.72

 defect

-0.68

undreds

-0.67

oxide

-0.67

ENE

-0.67

abytes

-0.65

POSITIVE LOGITS

 ACTIONS

0.83

ĨĴ

0.78

ãĥĢ

0.77

natureconservancy

0.74

 guided

0.71

 curric

0.68

å£«

0.67

 permitting

0.67

 aimed

0.67

guided

0.65

Activations Density 0.526%

terms related to policies, procedures, and decision-makers in governmental or organizational settings

terms related to policy-making and procedures

No Comments

No Known Activations