INDEX

Explanations

phrases related to making statements or declarations

oai_token-act-pair · gpt-3.5-turbo

references to significant events or statements made by public figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

helm

-0.67

blogspot

-0.64

ufact

-0.61

DEN

-0.61

MN

-0.61

ATED

-0.60

WER

-0.60

ãĥ¡

-0.59

 distingu

-0.58

 destro

-0.58

POSITIVE LOGITS

 bluff

1.04

 hotline

0.85

Cth

0.70

 kettle

0.67

 ugly

0.64

 Behavior

0.64

SourceFile

0.62

 derogatory

0.60

NCT

0.60

 Deity

0.58

Activations Density 0.133%

phrases related to making statements or declarations

references to significant events or statements made by public figures

No Comments

No Known Activations