INDEX

Explanations

words related to exerting influence or demands on someone or something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "pressure" and its various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

nam

-0.80

tein

-0.71

alian

-0.70

umbn

-0.70

clus

-0.68

gd

-0.67

 Acad

-0.67

yssey

-0.66

ICLE

-0.65

ithe

-0.65

POSITIVE LOGITS

 cooker

1.33

 pressure

1.10

pressure

1.06

 pressures

0.92

 exerted

0.91

 pressured

0.91

 pneum

0.89

 pressuring

0.79

 presses

0.74

 Pressure

0.74

Activations Density 0.015%

words related to exerting influence or demands on someone or something

instances of the word "pressure" and its various contexts

No Comments

No Known Activations