INDEX

Explanations

content related to government, opinions, and policy

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to governmental accountability and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Cub

-0.57

 sexes

-0.56

 visualization

-0.55

 Brit

-0.55

 classmate

-0.55

 teammate

-0.55

 cubes

-0.55

 occurrence

-0.54

Ov

-0.54

 Semin

-0.54

POSITIVE LOGITS

 appoint

0.86

erity

0.81

 legisl

0.78

 appointing

0.76

 veto

0.75

 enact

0.74

 arrog

0.73

 prag

0.72

 inaction

0.71

 wisely

0.70

Activations Density 1.168%

content related to government, opinions, and policy

phrases and terms related to governmental accountability and performance

No Comments

No Known Activations