INDEX

Explanations

words related to the United States or its citizens

oai_token-act-pair · gpt-3.5-turbo

references to Americans or American demographics

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

cer

-0.67

camera

-0.67

Initialized

-0.67

operation

-0.65

bol

-0.65

Za

-0.64

Sys

-0.64

type

-0.64

Drag

-0.62

rous

-0.62

POSITIVE LOGITS

hip

0.90

0.88

 living

0.86

who

0.81

 residing

0.81

 polled

0.79

ervative

0.79

 aged

0.79

 enrolled

0.78

ervatives

0.77

Activations Density 0.064%

words related to the United States or its citizens

references to Americans or American demographics

No Comments

No Known Activations