INDEX

Explanations

linguistic terms

oai_token-act-pair · gpt-3.5-turbo

gerund and participial forms of verbs

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

raviolet

-0.75

ĳå£«

-0.73

ĻĤ

-0.73

 Seym

-0.69

IFIED

-0.68

Ô

-0.65

 citiz

-0.63

 intervening

-0.62

Filename

-0.62

-+-+

-0.61

POSITIVE LOGITS

ttes

1.01

worth

1.01

heed

0.97

bury

0.93

ham

0.90

bian

0.89

tons

0.89

down

0.87

gren

0.86

gling

0.86

Activations Density 0.051%

linguistic terms

gerund and participial forms of verbs

No Comments

No Known Activations