INDEX

Explanations

names or titles associated with achievements or awards

oai_token-act-pair · gpt-3.5-turbo

terms related to prestigious awards and notable individuals

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

é¾įå¥ĳå£«

-0.66

LESS

-0.61

 Nicotine

-0.56

 Feast

-0.56

EStream

-0.55

FUL

-0.55

less

-0.55

 Dragonbound

-0.53

 Aber

-0.53

 Akin

-0.52

POSITIVE LOGITS

ª

1.02

·

0.99

©

0.97

ĩ

0.96

Ģ

0.94

ĺ

0.89

´

0.89

ī

0.89

¹

0.89

¬

0.89

Activations Density 0.493%

names or titles associated with achievements or awards

terms related to prestigious awards and notable individuals

No Comments

No Known Activations