INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to a character named Kra

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

payer

-0.80

 Beckham

-0.78

 à¨

-0.73

orative

-0.73

-0.72

sheet

-0.72

earable

-0.69

riad

-0.68

 Freddie

-0.68

iants

-0.68

POSITIVE LOGITS

Kra

1.10

ven

1.04

uth

0.97

Å¡

0.91

emer

0.87

lyak

0.84

unte

0.82

pps

0.82

eker

0.81

plin

0.81

Activations Density 0.005%

proper nouns

references to a character named Kra

No Comments

No Known Activations