INDEX

Explanations

words related to impact or strong emotions, possibly with a focus on physical force

oai_token-act-pair · gpt-3.5-turbo

words related to structural elements or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Irvine

-0.76

 Birch

-0.70

ulhu

-0.69

SAS

-0.69

 Kung

-0.67

 Amtrak

-0.67

 Garfield

-0.67

edi

-0.67

 casinos

-0.66

 shuffle

-0.65

POSITIVE LOGITS

stru

3.00

 maiden

1.97

rera

1.67

Dre

1.28

itten

1.25

 menstru

1.17

opausal

1.10

ov

1.06

 Maiden

0.96

 menstrual

0.90

Activations Density 0.044%

words related to impact or strong emotions, possibly with a focus on physical force

words related to structural elements or components

No Comments

No Known Activations