INDEX

Explanations

references to news organizations and their activities

oai_token-act-pair · gpt-3.5-turbo

references to specific news organizations

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

sale

-0.72

ayne

-0.71

genic

-0.71

 Miko

-0.69

olulu

-0.68

ptoms

-0.67

ortium

-0.66

 Metroid

-0.65

Aki

-0.64

icted

-0.64

POSITIVE LOGITS

utenberg

0.82

orters

0.77

WS

0.74

andowski

0.74

keepers

0.72

room

0.71

wat

0.70

 broadcasts

0.70

 jugg

0.70

 corps

0.69

Activations Density 0.261%

references to news organizations and their activities

references to specific news organizations

No Comments

No Known Activations