INDEX

Explanations

words related to a specific term "Snopes"

oai_token-act-pair · gpt-3.5-turbo

the presence of a specific name or label repeatedly mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 PowerPoint

-0.76

 Hezbollah

-0.75

TAIN

-0.75

66666666

-0.74

xual

-0.73

heid

-0.72

 Sunni

-0.71

upon

-0.68

ãĥĩ

-0.66

CPI

-0.64

POSITIVE LOGITS

ipers

1.06

uggle

1.05

ugg

1.04

Sn

1.04

icket

1.04

agging

1.02

igger

1.00

omore

0.98

utt

0.98

agged

0.96

Activations Density 0.006%

words related to a specific term "Snopes"

the presence of a specific name or label repeatedly mentioned in the text

No Comments

No Known Activations