INDEX

Explanations

references to specific entities, countries, and locations

oai_token-act-pair · gpt-3.5-turbo

key entities and terms related to political and economic structures

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

ERG

-0.55

Nar

-0.55

Sym

-0.53

cause

-0.53

onom

-0.52

Policy

-0.52

?????-?????-

-0.51

ãĤ§

-0.51

 listener

-0.51

ãĤª

-0.51

POSITIVE LOGITS

 respectively

0.88

.''.

0.82

0.72

.*

0.69

*.

0.69

).

0.68

.).

0.66

.''

0.66

,.

0.65

.)

0.63

Activations Density 0.758%

references to specific entities, countries, and locations

key entities and terms related to political and economic structures

No Comments

No Known Activations