INDEX

Explanations

phrases related to achieving victory or success

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "win" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bian

-0.66

agg

-0.59

 gearing

-0.58

rouch

-0.57

Factor

-0.56

miah

-0.56

 lapse

-0.56

appa

-0.56

 easing

-0.55

 Dwell

-0.55

POSITIVE LOGITS

now

0.98

nings

0.89

throp

0.88

ced

0.84

ners

0.80

ces

0.79

atown

0.78

ests

0.76

cing

0.73

hardt

0.73

Activations Density 0.049%

phrases related to achieving victory or success

occurrences of the word "win" in various contexts

No Comments

No Known Activations