INDEX

Explanations

phrases related to instructions or procedures

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol repeated throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 shack

-0.73

itably

-0.70

 scatter

-0.68

 decomp

-0.68

bed

-0.68

 machine

-0.68

 collecting

-0.66

 supermarket

-0.66

 scattering

-0.66

 coast

-0.66

POSITIVE LOGITS

¹

0.93

£

0.92

¡

0.89

ONSORED

0.86

gypt

0.86

į

0.83

ł

0.82

ĸļ

0.82

 Ibid

0.81

º

0.81

Activations Density 0.412%

phrases related to instructions or procedures

instances of a specific character or symbol repeated throughout the text

No Comments

No Known Activations