INDEX

Explanations

references to claims and evidence supporting arguments

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

nouns that represent concrete objects or entities placed in prepositional phrases.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

eradish

-0.47

 怎样

-0.39

 appelez

-0.35

ografija

-0.35

DockStyle

-0.35

 isSet

-0.33

delwed

-0.32

asteroide

-0.32

drawn

-0.32

imab

-0.31

POSITIVE LOGITS

 into

0.69

 onto

0.66

 closer

0.59

Ӕ

0.56

 squarely

0.53

Composable

0.52

 defaultstate

0.52

 firmly

0.52

endregion

0.51

 astray

0.49

Activations Density 0.209%

references to claims and evidence supporting arguments

nouns that represent concrete objects or entities placed in prepositional phrases.

No Comments

No Known Activations