INDEX

Explanations

instances of the word "veto" with varying levels of relevance

oai_token-act-pair · gpt-3.5-turbo

terms related to veto power and legislative authority

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

asma

-0.79

istics

-0.78

ndra

-0.76

ewitness

-0.73

 Feet

-0.73

EAR

-0.72

annis

-0.72

arist

-0.71

MPG

-0.70

Sea

-0.67

POSITIVE LOGITS

 veto

1.14

 vetoed

1.01

zai

0.92

 amnesty

0.74

 Feinstein

0.71

 decree

0.69

 ratification

0.69

 slate

0.67

 authorizing

0.67

 override

0.67

Activations Density 0.025%

instances of the word "veto" with varying levels of relevance

terms related to veto power and legislative authority

No Comments

No Known Activations