INDEX

Explanations

the name "David" and its variations in multiple contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 hant

-0.66

+#+

-0.65

Butyl

-0.65

antee

-0.63

poss

-0.61

ReusableCell

-0.60

mms

-0.60

bunt

-0.60

unhofer

-0.60

/#/

-0.59

POSITIVE LOGITS

 David

1.40

 Davids

1.32

David

1.31

DAVID

1.30

 DAVID

1.26

 david

1.16

david

1.08

avid

1.03

 Davie

0.98

 Davido

0.98

Activations Density 0.050%

the name "David" and its variations in multiple contexts

No Comments

No Known Activations