INDEX

Explanations

mentions of "Pew Research" or "Pew Research Center" in the text

oai_token-act-pair · gpt-3.5-turbo

references to the Pew Research Center and its surveys

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

 Yanuk

-0.71

 gearing

-0.64

 disorderly

-0.63

 Yanukovych

-0.62

stood

-0.62

 Runner

-0.61

 forgiven

-0.61

 Royals

-0.60

 Malf

-0.60

 ultras

-0.59

POSITIVE LOGITS

aukee

1.23

Die

0.98

 Institution

0.97

 Research

0.96

Research

0.83

sonian

0.83

Pew

0.83

sylvania

0.81

Poll

0.80

 Hispanic

0.79

Activations Density 0.034%

mentions of "Pew Research" or "Pew Research Center" in the text

references to the Pew Research Center and its surveys

No Comments

No Known Activations