INDEX

Explanations

the word "pant" appearing with different suffixes

oai_token-act-pair · gpt-3.5-turbo

variations of the word "pantheon."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UTION

-0.74

 Sett

-0.74

 Carbuncle

-0.74

sett

-0.67

GC

-0.66

FORMATION

-0.65

Alz

-0.63

 Commodore

-0.62

displayText

-0.62

 Kingston

-0.60

POSITIVE LOGITS

heon

1.37

 pant

1.35

 Pant

0.97

 newcom

0.88

ĸļ

0.87

icip

0.87

agraph

0.86

zsche

0.85

agonists

0.84

hetically

0.83

Activations Density 0.006%

the word "pant" appearing with different suffixes

variations of the word "pantheon."

No Comments

No Known Activations