INDEX

Explanations

phrases beginning with the word "it" and followed by some other content

oai_token-act-pair · gpt-3.5-turbo

the pronoun "it" used 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

warning

-0.64

 Angola

-0.57

 Breast

-0.55

OUND

-0.55

 Kansas

-0.54

 Polk

-0.53

 Tokyo

-0.52

 Dayton

-0.52

 Sadd

-0.52

 funer

-0.51

POSITIVE LOGITS

chy

1.35

alian

1.21

self

1.15

atic

1.02

asca

1.02

anium

0.98

unes

0.97

iner

0.93

alia

0.93

atically

0.88

Activations Density 0.288%

phrases beginning with the word "it" and followed by some other content

the pronoun "it" used in various contexts

No Comments

No Known Activations