INDEX

Explanations

references to fitting or size comparisons

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fit" and its variations

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

wcs

-0.84

externalActionCode

-0.77

cipl

-0.73

icious

-0.70

iolet

-0.68

cember

-0.66

ourage

-0.66

 livest

-0.64

ials

-0.63

ãĥ£

-0.63

POSITIVE LOGITS

 snug

1.00

fit

0.87

gerald

0.82

 fits

0.78

ÃįÃį

0.78

Fit

0.75

 onto

0.73

nah

0.73

fit

0.72

 into

0.72

Activations Density 0.015%

references to fitting or size comparisons

instances of the word "fit" and its variations

No Comments

No Known Activations