INDEX

Explanations

references to social media actions, specifically related to sharing content

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Share"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

schild

-0.81

panic

-0.75

 destro

-0.74

sbm

-0.73

 compr

-0.73

undai

-0.72

morrow

-0.71

©¶æ

-0.68

bley

-0.68

anwhile

-0.68

POSITIVE LOGITS

holders

1.22

holder

1.16

ership

0.99

ables

0.90

 Share

0.87

cro

0.83

able

0.83

Tweet

0.82

holding

0.81

edin

0.79

Activations Density 0.017%

references to social media actions, specifically related to sharing content

instances of the word "Share"

No Comments

No Known Activations