INDEX

Explanations

mentions of religious figures and locations like nuns, Sisters, and convents

oai_token-act-pair · gpt-3.5-turbo

references to nuns and their roles in 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

à¸

-0.72

eters

-0.66

azing

-0.65

ozy

-0.64

activity

-0.64

ðĿ

-0.63

resp

-0.62

HAM

-0.61

ERG

-0.61

=-=-=-=-

-0.61

POSITIVE LOGITS

 nuns

1.06

nery

1.01

nun

0.97

 convent

0.89

 Sisters

0.87

 Sister

0.84

 choir

0.82

cess

0.82

 Lucia

0.80

ipation

0.78

Activations Density 0.017%

mentions of religious figures and locations like nuns, Sisters, and convents

references to nuns and their roles in various contexts

No Comments

No Known Activations