INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

characters or symbols that are likely non-standard or corrupted text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

çīĪ

-0.79

;;;;;;;;;;;;

-0.70

mbudsman

-0.66

hran

-0.66

OTUS

-0.65

vP

-0.63

POL

-0.63

wi

-0.63

DCS

-0.62

 Discuss

-0.61

POSITIVE LOGITS

è¦

0.81

fter

0.70

inet

0.67

 Thrust

0.66

 Ballard

0.65

flush

0.65

 Beet

0.65

 Kund

0.64

than

0.64

insured

0.63

Activations Density 0.000%

proper nouns

characters or symbols that are likely non-standard or corrupted text

No Comments

No Known Activations