INDEX

Explanations

words related to fetishes

oai_token-act-pair · gpt-3.5-turbo

terms related to fetal tissue and associated medical or ethical discussions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ĨĴ

-0.75

 Principles

-0.67

VERTISEMENT

-0.65

Guide

-0.64

é»Ĵ

-0.63

 Diversity

-0.63

EngineDebug

-0.63

 Coverage

-0.63

soType

-0.63

 Nationwide

-0.62

POSITIVE LOGITS

fet

1.09

fet

1.05

tered

1.04

ches

0.98

tering

0.97

ched

0.94

ters

0.93

ting

0.92

ter

0.89

imes

0.89

Activations Density 0.021%

words related to fetishes

terms related to fetal tissue and associated medical or ethical discussions

No Known Activations