INDEX

Explanations

phrases related to hindering or preventing something

oai_token-act-pair · gpt-3.5-turbo

concepts related to prevention or deterrence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

olini

-0.76

 rooft

-0.71

 Patriarch

-0.70

ioch

-0.69

ocalypse

-0.69

oln

-0.66

ocene

-0.65

enhagen

-0.65

 halls

-0.64

oway

-0.64

POSITIVE LOGITS

ministic

1.82

minist

1.51

rence

1.02

ior

0.97

gent

0.96

red

0.91

ried

0.89

ring

0.87

ply

0.86

rer

0.84

Activations Density 0.025%

phrases related to hindering or preventing something

concepts related to prevention or deterrence

No Comments

No Known Activations