INDEX

Explanations

words related to societal, political, or environmental pressure

oai_token-act-pair · gpt-3.5-turbo

references to public pressure and its impact on decision-making

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

tein

-0.85

ithe

-0.74

\\\\\\\\

-0.73

umbn

-0.73

merce

-0.71

sterdam

-0.68

alian

-0.68

initions

-0.68

istic

-0.67

istically

-0.67

POSITIVE LOGITS

 cooker

1.39

 exerted

1.12

pressure

1.03

 pressure

1.01

 pressures

0.88

 pressured

0.83

 pressuring

0.82

 pneum

0.78

 tactics

0.77

 valve

0.75

Activations Density 0.027%

words related to societal, political, or environmental pressure

references to public pressure and its impact on decision-making

No Comments

No Known Activations