INDEX

Explanations

terms related to composition and structuring

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

PerformLayout

-0.47

提到

-0.45

Voodoo

-0.44

testcase

-0.43

ęć

-0.42

 KeyCode

-0.40

Appropriate

-0.40

 Hines

-0.40

gın

-0.40

Trivia

-0.40

POSITIVE LOGITS

 composing

1.46

 compose

1.39

composed

1.36

 compos

1.32

 composition

1.32

 Composition

1.31

 compone

1.26

 compositions

1.25

 composed

1.24

Composition

1.24

Activations Density 0.286%

terms related to composition and structuring

No Comments

No Known Activations