INDEX

Explanations

the word "like" in various contexts

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

references to companies

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ells

-0.73

atform

-0.72

ulty

-0.71

ival

-0.71

ennes

-0.69

inct

-0.69

ictional

-0.68

 istg

-0.66

itta

-0.66

ysical

-0.65

POSITIVE LOGITS

lihood

1.10

lier

0.97

liest

0.93

 ours

0.92

 minded

0.86

 hers

0.83

minded

0.82

 yours

0.79

 theirs

0.76

pired

0.72

Activations Density 0.083%

the word "like" in various contexts

references to companies

No Comments

No Known Activations