INDEX

Explanations

the word "Del" with varying intensity

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Del" or related names in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.92

 GOODMAN

-0.80

anwhile

-0.80

displayText

-0.79

PsyNetMessage

-0.76

 actionGroup

-0.76

uyomi

-0.73

 Asylum

-0.73

)=(

-0.72

Ĥİ

-0.72

POSITIVE LOGITS

ayed

1.07

usional

1.00

ivering

0.95

ivered

0.95

aware

0.95

ivery

0.95

phi

0.92

iver

0.91

iber

0.89

ivers

0.85

Activations Density 0.004%

the word "Del" with varying intensity

mentions of the name "Del" or related names in various contexts

No Comments

No Known Activations