INDEX

Explanations

proper nouns with the prefix "Kan"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Kan" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 charism

-0.66

Ö¼

-0.64

 FIGHT

-0.61

 Proced

-0.60

 CARD

-0.60

IBLE

-0.59

 Trident

-0.58

tsky

-0.58

 reception

-0.57

 luck

-0.57

POSITIVE LOGITS

ji

1.18

thal

1.12

awa

1.06

erva

1.03

ataka

1.03

ju

0.99

hai

0.97

ako

0.95

eki

0.95

quet

0.94

Activations Density 0.028%

proper nouns with the prefix "Kan"

mentions of the word "Kan" and its variations

No Comments

No Known Activations