INDEX

Explanations

references to people named Louis

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Louis"

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

BOOK

-0.90

lished

-0.68

ilk

-0.68

ulum

-0.65

mit

-0.64

ãĤ§

-0.62

×Ĳ

-0.62

thia

-0.62

GAME

-0.61

bley

-0.61

POSITIVE LOGITS

XVI

1.02

CK

1.00

Vu

0.99

XIV

0.95

iana

0.91

bourg

0.88

 XIII

0.82

 Angeles

0.80

XV

0.79

 Armstrong

0.78

Activations Density 0.007%

references to people named Louis

occurrences of the name "Louis"

No Comments

No Known Activations