INDEX

Explanations

organizations or government agencies

oai_token-act-pair · gpt-3.5-turbo

occurrences of government or regulatory agency names, particularly in relation to alcohol, firearms, and economic topics

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

auga

-0.82

gow

-0.77

borgh

-0.76

paces

-0.70

piece

-0.68

rises

-0.65

warts

-0.65

 certs

-0.65

osaurus

-0.63

iour

-0.62

POSITIVE LOGITS

 Statistics

0.95

 Investigation

0.91

 Statistical

0.85

 Consumer

0.83

 Alcohol

0.83

 Standards

0.80

ãĥĥãĥĪ

0.79

 Investigative

0.79

 Forestry

0.77

 Interactive

0.76

Activations Density 0.034%

organizations or government agencies

occurrences of government or regulatory agency names, particularly in relation to alcohol, firearms, and economic topics

No Comments

No Known Activations