INDEX

Explanations

Twitter handles and quotations from NBC news

oai_token-act-pair · gpt-3.5-turbo

mentions of news organizations and their programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Riy

-0.93

yip

-0.90

 sword

-0.89

Xie

-0.87

Sword

-0.86

Rim

-0.83

Tang

-0.82

 Tang

-0.80

ãĢ

-0.78

 graphene

-0.77

POSITIVE LOGITS

NBC

2.15

CBS

2.09

NBC

2.04

CBS

1.97

 Comcast

1.56

 CNBC

1.52

ABC

1.43

ABC

1.40

 Showtime

1.38

 MSNBC

1.36

Activations Density 0.249%

Twitter handles and quotations from NBC news

mentions of news organizations and their programming

No Comments

No Known Activations