INDEX

Explanations

proper nouns followed by possessive form and a subsequent descriptor

oai_token-act-pair · gpt-3.5-turbo

the letter 's' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

esp

-0.70

Brit

-0.66

Compare

-0.66

LINE

-0.65

SHA

-0.63

java

-0.63

Boo

-0.61

Buzz

-0.61

Past

-0.61

PLAY

-0.60

POSITIVE LOGITS

own

0.93

 inability

0.84

 Office

0.84

avior

0.83

 successor

0.82

ullivan

0.82

 newest

0.81

 mandate

0.80

essions

0.79

 flagship

0.79

Activations Density 0.182%

proper nouns followed by possessive form and a subsequent descriptor

the letter 's' in various contexts

No Comments

No Known Activations