INDEX

Explanations

mentions of locks or actions related to locking things

oai_token-act-pair · gpt-3.5-turbo

terms related to security or confinement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

issance

-0.92

LV

-0.78

OTAL

-0.66

acio

-0.66

resso

-0.65

 Lynd

-0.64

abama

-0.63

schild

-0.63

abwe

-0.63

ilater

-0.62

POSITIVE LOGITS

picking

1.22

heed

1.13

pick

0.97

creen

0.97

lear

0.94

hold

0.90

 horns

0.90

door

0.89

downs

0.87

hart

0.84

Activations Density 0.025%

mentions of locks or actions related to locking things

terms related to security or confinement

No Comments

No Known Activations