INDEX

Explanations

phrases containing the word "said" followed by information or quotation

oai_token-act-pair · gpt-3.5-turbo

quotes or statements attributed to individuals

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

à¦

-0.79

FL

-0.74

 ILCS

-0.71

ãĥ¤

-0.64

vez

-0.63

Made

-0.63

tumblr

-0.62

Ò

-0.60

protected

-0.60

INT

-0.59

POSITIVE LOGITS

 anecd

0.84

:"

0.76

terday

0.68

 bluntly

0.64

ratulations

0.64

:]

0.63

 persu

0.61

pse

0.61

 recalling

0.60

inery

0.60

Activations Density 0.163%

phrases containing the word "said" followed by information or quotation

quotes or statements attributed to individuals

No Known Activations