INDEX

Explanations

references to the word "Pin."

oai_token-act-pair · gpt-3.5-turbo

references to "Pin" or related products

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

anwhile

-0.95

mble

-0.80

IGH

-0.75

ngth

-0.73

ĨĴ

-0.72

earch

-0.72

gaard

-0.69

 behav

-0.69

UGH

-0.69

mberg

-0.68

POSITIVE LOGITS

ochet

1.16

ning

1.15

ned

1.04

pend

0.85

wheel

0.82

ball

0.79

ners

0.79

point

0.78

ched

0.78

ako

0.78

Activations Density 0.019%

references to the word "Pin."

references to "Pin" or related products

No Comments

No Known Activations