INDEX

Explanations

phrases related to determination or assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AddTagHelper

-0.73

writeFieldEnd

-0.71

Cass

-0.70

Agg

-0.65

 transfieras

-0.65

Felic

-0.65

حياته

-0.64

spesies

-0.64

﹧

-0.63

addMessage

-0.62

POSITIVE LOGITS

 naturaleza

0.41

 Aetna

0.40

 voglio

0.40

 hierro

0.40

 ontwerp

0.40

 sostenibilidad

0.39

 Ondo

0.39

 nutrición

0.38

 toreb

0.38

 restauración

0.37

Activations Density 0.347%

phrases related to determination or assessment

No Comments

No Known Activations