INDEX

Explanations

references to music records or albums

oai_token-act-pair · gpt-3.5-turbo

references to music records and their releases

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

 Liang

-0.75

Ĭ±

-0.73

laus

-0.72

hin

-0.69

 Dent

-0.68

cius

-0.68

 hypert

-0.64

aukee

-0.64

htt

-0.63

 Leth

-0.63

POSITIVE LOGITS

 albums

0.93

stores

0.89

 labels

0.84

isphere

0.84

 cassette

0.83

orders

0.83

company

0.83

 producer

0.77

 label

0.76

 Label

0.76

Activations Density 0.034%

references to music records or albums

references to music records and their releases

No Comments

No Known Activations