INDEX

Explanations

phrases related to theft and related crimes

oai_token-act-pair · gpt-3.5-turbo

terms related to theft and property crimes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

paren

-0.73

eele

-0.73

enegger

-0.71

ULE

-0.70

ellar

-0.70

ombs

-0.70

airo

-0.69

ayn

-0.68

xus

-0.67

mos

-0.66

POSITIVE LOGITS

 spree

1.04

 Theft

0.89

 prevention

0.86

 synd

0.79

 theft

0.75

 motive

0.67

 robbery

0.67

 rampage

0.66

 detection

0.66

 coefficient

0.66

Activations Density 0.024%

phrases related to theft and related crimes

terms related to theft and property crimes

No Comments

No Known Activations