INDEX

Explanations

references to professional roles and responsibilities

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

aarrggbb

-0.63

astify

-0.51

/**

-0.50

 MENTAL

-0.49

 ligiloj

-0.46

PutPixel

-0.46

 Babi

-0.46

.*")]

-0.45

 RELATIONS

-0.45

 LANGUAGE

-0.45

POSITIVE LOGITS

Życiorys

0.38

 enlisted

0.36

 profiled

0.34

 geçir

0.33

 esterno

0.33

 served

0.32

 prior

0.32

具有

0.31

 życia

0.31

clyde

0.31

Activations Density 0.205%

references to professional roles and responsibilities

No Comments

No Known Activations