INDEX

Explanations

references to individuals and biographical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Dominique

-0.43

 stick

-0.43

pad

-0.43

 vandal

-0.42

 Schloß

-0.40

 Laing

-0.40

Fay

-0.40

Dino

-0.39

 Alvarado

-0.37

 Arno

-0.37

POSITIVE LOGITS

anne

0.64

Cherry

0.60

cherry

0.59

 cherry

0.57

 Cherry

0.57

SequentialGroup

0.57

 Ches

0.56

 cheer

0.56

 Cher

0.54

bi

0.54

Activations Density 0.520%

references to individuals and biographical contexts

No Comments

No Known Activations