INDEX

Explanations

text related to travel routes and journeys

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "en-"

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

Leaks

-0.78

hetic

-0.69

orry

-0.67

 Kard

-0.66

 Reed

-0.64

ays

-0.63

zero

-0.63

 Ridley

-0.63

 Hallow

-0.63

 Loft

-0.62

POSITIVE LOGITS

en

3.53

En

1.55

En

1.47

ent

1.28

EN

1.26

eng

1.24

enc

1.18

ens

1.09

 enchanted

1.09

por

1.07

Activations Density 0.020%

text related to travel routes and journeys

instances of the prefix "en-"

No Comments

No Known Activations