INDEX

Explanations

the word "forum" and related terms in the text

oai_token-act-pair · gpt-3.5-turbo

terms related to online forums and discussions

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

Not in Any Lists

No Comments

Negative Logits

lys

-0.76

efe

-0.72

ochond

-0.64

meter

-0.64

sea

-0.64

mson

-0.64

ocr

-0.63

stroke

-0.63

zman

-0.62

ectar

-0.62

POSITIVE LOGITS

 moderators

0.92

 postings

0.89

 moderator

0.89

 thread

0.88

 posts

0.84

 discussion

0.84

 forums

0.84

 threads

0.83

 forum

0.82

 moder

0.82

Activations Density 0.051%

the word "forum" and related terms in the text

terms related to online forums and discussions

No Comments

No Known Activations