INDEX

Explanations

adverbs used to express certainty or opinion

oai_token-act-pair · gpt-3.5-turbo

words indicating levels of certainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iage

-0.66

anners

-0.61

kefeller

-0.60

lain

-0.56

prus

-0.55

ategory

-0.55

itance

-0.55

\'

-0.55

UGE

-0.55

riers

-0.54

POSITIVE LOGITS

 surprisingly

0.75

 importantly

0.74

 unconsciously

0.74

 impro

0.73

 anyway

0.73

 unwittingly

0.73

 guessed

0.72

asionally

0.71

 ironically

0.71

0.70

Activations Density 0.119%

adverbs used to express certainty or opinion

words indicating levels of certainty or speculation

No Comments

No Known Activations