INDEX

Explanations

words related to importance or seriousness

oai_token-act-pair · gpt-3.5-turbo

references to essential or vital elements in various contexts

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

boat

-0.77

âĢ¢âĢ¢âĢ¢âĢ¢

-0.76

owship

-0.74

UAL

-0.74

 Polo

-0.73

Mania

-0.73

Haunted

-0.72

bows

-0.72

Pic

-0.71

ila

-0.71

POSITIVE LOGITS

 importance

0.92

 components

0.82

arial

0.80

 infrastructure

0.78

jun

0.76

 Role

0.76

 acclaim

0.76

 component

0.74

 elements

0.73

ostic

0.71

Activations Density 0.019%

words related to importance or seriousness

references to essential or vital elements in various contexts

No Comments

No Known Activations