INDEX

Explanations

words related to traps

oai_token-act-pair · gpt-3.5-turbo

references to traps or trapping mechanisms

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

edly

-0.84

sis

-0.81

issance

-0.77

league

-0.73

 normalized

-0.73

Merit

-0.65

Ħ¢

-0.64

kees

-0.63

eds

-0.62

verty

-0.62

POSITIVE LOGITS

door

1.47

doors

1.37

finding

0.96

trap

0.94

 traps

0.89

idon

0.85

 trap

0.82

 Trap

0.79

ERY

0.79

 Hole

0.75

Activations Density 0.028%

words related to traps

references to traps or trapping mechanisms

No Comments

No Known Activations