INDEX

Explanations

mentions of news broadcasters

oai_token-act-pair · gpt-3.5-turbo

mentions of broadcasters and broadcasting entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

illard

-0.81

othes

-0.69

BuyableInstoreAndOnline

-0.68

 Bruins

-0.65

leans

-0.62

hiro

-0.62

 Venice

-0.60

 Martian

-0.59

udes

-0.59

hens

-0.59

POSITIVE LOGITS

 broadcaster

1.22

 broadcasters

1.04

caster

0.91

levision

0.89

casters

0.87

 Broadcasting

0.83

 broadcasting

0.81

 Broadcast

0.79

 licensee

0.78

 nodd

0.77

Activations Density 0.008%

mentions of news broadcasters

mentions of broadcasters and broadcasting entities

No Comments

No Known Activations