INDEX

Explanations

mentions of the word "Saf"

oai_token-act-pair · gpt-3.5-turbo

references to the word "Saf" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lore

-0.74

anooga

-0.70

hatt

-0.69

overs

-0.69

lift

-0.69

ional

-0.65

 boiling

-0.64

 baptism

-0.64

iste

-0.64

 Dragonbound

-0.64

POSITIVE LOGITS

mented

1.03

eco

0.96

eties

0.95

vous

0.95

meric

0.90

mbol

0.86

PLE

0.86

ple

0.80

egu

0.79

saf

0.78

Activations Density 0.059%

mentions of the word "Saf"

references to the word "Saf" in various contexts

No Comments

No Known Activations