INDEX

Explanations

instances of the word "hole" along with some context around it

oai_token-act-pair · gpt-3.5-turbo

mentions of "hole"

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

cia

-0.86

uscript

-0.69

NetMessage

-0.66

 Idle

-0.66

author

-0.65

issance

-0.65

lux

-0.65

 residues

-0.65

 livest

-0.64

Bal

-0.64

POSITIVE LOGITS

 hole

1.28

 Hole

1.21

 holes

1.20

hole

1.17

 drilled

1.05

holes

0.98

izons

0.96

dug

0.96

 punched

0.81

 canyon

0.80

Activations Density 0.020%

instances of the word "hole" along with some context around it

mentions of "hole"

No Comments

No Known Activations