INDEX

Explanations

mentions of being physically stuck or restricted.

oai_token-act-pair · gpt-3.5-turbo

instances of the word "trapped"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

edly

-0.82

eds

-0.76

sych

-0.72

issance

-0.68

esan

-0.68

 praises

-0.60

office

-0.59

minus

-0.59

 Carbuncle

-0.59

ss

-0.59

POSITIVE LOGITS

 trapped

1.00

ĸļ

0.83

 trapping

0.82

©¶æ¥µ

0.81

ÃįÃį

0.80

ngth

0.79

ÃĥÃĤ

0.74

ModLoader

0.73

door

0.72

ãĥĺ

0.71

Activations Density 0.010%

mentions of being physically stuck or restricted.

instances of the word "trapped"

No Comments

No Known Activations