INDEX

Explanations

references to camps or camp-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

principalColumn

-0.46

yyb

-0.44

Capa

-0.42

CLE

-0.41

ulam

-0.40

pidou

-0.40

vinas

-0.40

uisine

-0.40

tangentMode

-0.39

setas

-0.39

POSITIVE LOGITS

 camp

0.61

Words

0.55

words

0.55

 ModelExpression

0.54

 Words

0.49

cmd

0.46

 words

0.46

 Worten

0.45

rophoresis

0.45

Portail

0.45

Activations Density 0.142%

references to camps or camp-related topics

No Comments

No Known Activations