INDEX

Explanations

references to volumes or numerical identifiers

oai_token-act-pair · gpt-3.5-turbo

items related to publication issues and volume numbers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

riad

-0.89

ufact

-0.70

leneck

-0.69

 Cheong

-0.68

behind

-0.67

intosh

-0.63

agascar

-0.62

alore

-0.62

alty

-0.61

eele

-0.61

POSITIVE LOGITS

wagen

1.21

ioxide

0.86

Ħ¢

0.86

ĺ

0.83

§

0.82

³

0.81

¦

0.80

Ń·

0.79

Ĥİ

0.78

ł

0.78

Activations Density 0.066%

references to volumes or numerical identifiers

items related to publication issues and volume numbers

No Comments

No Known Activations