INDEX

Explanations

symbols or punctuations used for emphasis or separation between thoughts

oai_token-act-pair · gpt-3.5-turbo

the presence of a specific symbol or character sequence

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

 scatter

-0.72

 decomp

-0.71

 mixed

-0.68

 exhausted

-0.68

 unmarked

-0.65

etsy

-0.63

romy

-0.62

 oldest

-0.62

 memoir

-0.61

fid

-0.61

POSITIVE LOGITS

âĹ¼

1.01

¬

0.94

º

0.93

âĢł

0.89

Ĵ

0.89

§

0.89

į

0.88

âĢķ

0.86

Â¯

0.86

ĳ

0.85

Activations Density 0.380%

symbols or punctuations used for emphasis or separation between thoughts

the presence of a specific symbol or character sequence

No Comments

No Known Activations