INDEX

Explanations

mentions of names in journalistic or political contexts

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

DragonMagazine

-0.73

 lockout

-0.66

tumblr

-0.65

aturday

-0.63

 disproportion

-0.61

berra

-0.61

intensive

-0.60

 groundwork

-0.60

successfully

-0.60

 periodic

-0.60

POSITIVE LOGITS

Said

0.92

 said

0.85

 Said

0.80

 replied

0.79

 wrote

0.73

 told

0.73

 exclaimed

0.72

said

0.71

 joked

0.70

 elaborated

0.70

Activations Density 0.236%

mentions of names in journalistic or political contexts

proper nouns, specifically names of people

No Comments

No Known Activations