INDEX

Explanations

names of news organizations and media outlets

oai_token-act-pair · gpt-3.5-turbo

mentions of news sources or media outlets

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

locks

-0.90

 bonding

-0.84

 leveling

-0.79

activity

-0.76

 balancing

-0.72

abis

-0.70

ware

-0.69

 inhibitors

-0.67

 upgr

-0.67

âĻ¥

-0.67

POSITIVE LOGITS

 Huffington

1.32

 Newsweek

1.26

NYT

1.20

CNN

1.20

 MSNBC

1.18

 Politico

1.15

 CNBC

1.15

 Reuters

1.14

 Newsp

1.13

NBC

1.13

Activations Density 0.172%

names of news organizations and media outlets

mentions of news sources or media outlets

No Comments

No Known Activations