INDEX

Explanations

superlatives indicating greatness or excellence

oai_token-act-pair · gpt-3.5-turbo

superlative expressions and claims of being the "most" or "best" in a category

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

resy

-0.75

seless

-0.73

oute

-0.70

insk

-0.70

arity

-0.70

yang

-0.66

erest

-0.65

 Cosponsors

-0.64

lav

-0.63

rage

-0.62

POSITIVE LOGITS

 recorded

0.93

 heard

0.87

 dreamed

0.85

 seen

0.83

 imagined

0.83

 imaginable

0.79

 bestowed

0.75

agher

0.74

 assembled

0.73

 attained

0.72

Activations Density 0.016%

superlatives indicating greatness or excellence

superlative expressions and claims of being the "most" or "best" in a category

No Comments

No Known Activations