INDEX

Explanations

mentions of internet censorship and related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to internet censorship and freedom of expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

forth

-0.71

 beforehand

-0.63

 Nieto

-0.58

istically

-0.57

naires

-0.56

pil

-0.56

ted

-0.56

 Fren

-0.55

 astron

-0.53

 suprem

-0.53

POSITIVE LOGITS

BuyableInstoreAndOnline

1.00

cloneembedreportprint

0.81

thumbnails

0.79

 guiActiveUnfocused

0.78

malink

0.78

umbnails

0.73

 Featured

0.73

 guiActive

0.72

osponsors

0.71

embed

0.70

Activations Density 0.466%

mentions of internet censorship and related terms

terms related to internet censorship and freedom of expression

No Comments

No Known Activations