INDEX

Explanations

mentions of the word "Gen" followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to the term "Gen" and related contexts

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

cffffcc

-0.77

landish

-0.70

SourceFile

-0.68

 Hour

-0.63

 Burning

-0.63

 Heard

-0.62

rentice

-0.62

letal

-0.62

TPPStreamerBot

-0.61

ding

-0.61

POSITIVE LOGITS

uine

1.14

ocide

1.07

omics

1.00

iuses

0.94

alogy

0.93

omic

0.93

Gen

0.88

uin

0.87

otyp

0.83

oma

0.80

Activations Density 0.005%

mentions of the word "Gen" followed by a number

references to the term "Gen" and related contexts

No Comments

No Known Activations