INDEX

Explanations

references to books

oai_token-act-pair · gpt-3.5-turbo

references to books and their publication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Bots

-0.67

Yin

-0.66

 distant

-0.65

hap

-0.64

ylon

-0.64

xon

-0.63

sembly

-0.63

Xi

-0.63

00200000

-0.61

 Lumpur

-0.60

POSITIVE LOGITS

stores

1.53

seller

1.24

marks

1.20

shop

1.17

marked

1.06

worms

1.03

worm

1.03

cases

1.02

itatively

1.02

keeping

1.00

Activations Density 0.039%

references to books

references to books and their publication

No Comments

No Known Activations