INDEX

Explanations

specific mentions of the word "gorillas"

oai_token-act-pair · gpt-3.5-turbo

references to gorillas

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Hath

-0.76

çĦ

-0.72

 pree

-0.68

NC

-0.65

ALE

-0.64

Adv

-0.64

 Disability

-0.63

ŀ

-0.63

nder

-0.62

tie

-0.62

POSITIVE LOGITS

illas

1.48

terday

1.09

unta

0.90

cules

0.88

xon

0.83

uca

0.83

ques

0.83

ervatives

0.82

ervative

0.79

emonium

0.78

Activations Density 0.006%

specific mentions of the word "gorillas"

references to gorillas

No Comments

No Known Activations