INDEX

Explanations

comparative terms and concepts indicating superiority or inferiority

oai_token-act-pair · gpt-3.5-turbo

references to superiority and inferiority among groups or entities

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

BRE

-0.92

mberg

-0.88

 Dresden

-0.87

gren

-0.79

RPG

-0.78

MG

-0.78

SN

-0.74

mitt

-0.73

è¦ļéĨĴ

-0.73

OWS

-0.71

POSITIVE LOGITS

 superior

0.89

 dilig

0.86

 inferior

0.82

 grades

0.78

 educ

0.77

intendent

0.76

 intellect

0.75

 judgement

0.72

 nomine

0.72

iour

0.72

Activations Density 0.010%

comparative terms and concepts indicating superiority or inferiority

references to superiority and inferiority among groups or entities

No Comments

No Known Activations