INDEX

Explanations

words related to the human body

oai_token-act-pair · gpt-3.5-turbo

mentions of body and body image

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hoover

-0.80

 Kafka

-0.71

 Clover

-0.71

Ans

-0.68

ãĥĻ

-0.68

Pis

-0.68

 Booth

-0.67

Nex

-0.67

 Dickens

-0.62

 Jarrett

-0.62

POSITIVE LOGITS

guards

1.34

builders

1.19

guard

1.19

building

1.18

builder

1.14

weight

1.02

parts

1.01

 politic

0.94

wash

0.92

anguage

0.91

Activations Density 0.033%

words related to the human body

mentions of body and body image

No Comments

No Known Activations