INDEX

Explanations

excerpts or snippets of information from different sources

oai_token-act-pair · gpt-3.5-turbo

phrases indicating excerpts or examples from various sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

lees

-0.85

å£«

-0.76

Ħ¢

-0.75

Thom

-0.71

©¶æ¥µ

-0.69

aults

-0.69

Austral

-0.68

 Traps

-0.66

¥µ

-0.65

ĸļ

-0.65

POSITIVE LOGITS

 excerpt

1.11

 illustrating

0.97

 synopsis

0.94

 rundown

0.94

:-

0.92

 snippet

0.88

:(

0.86

 summary

0.86

 nutshell

0.85

*:

0.83

Activations Density 0.178%

excerpts or snippets of information from different sources

phrases indicating excerpts or examples from various sources

No Comments

No Known Activations