INDEX

Explanations

phrases indicating agreement or similarity

oai_token-act-pair · gpt-3.5-turbo

instances of the word "alike."

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

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

ohyd

-0.68

someone

-0.68

Georg

-0.68

](

-0.65

OLOG

-0.65

 Penal

-0.63

Ô

-0.63

Ö¼

-0.63

Emb

-0.63

olid

-0.62

POSITIVE LOGITS

 alike

1.23

lihood

1.12

 sexes

0.89

 minded

0.82

soever

0.79

 nodd

0.74

!--

0.73

sheets

0.71

minded

0.69

 fascinated

0.69

Activations Density 0.009%

phrases indicating agreement or similarity

instances of the word "alike."

No Comments

No Known Activations