INDEX

Explanations

names of individuals involved in various interactions and activities

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

 CURIAM

-0.54

transQ

-0.52

chesse

-0.47

 politiet

-0.47

føl

-0.47

➯

-0.47

versible

-0.46

Biographie

-0.46

 itſelf

-0.46

ledning

-0.45

POSITIVE LOGITS

 counterparts

0.42

ագրություններ

0.40

 otomatig

0.39

0.37

 counterpart

0.35

 stead

0.35

发表于

0.34

 Schließlich

0.33

WithEmail

0.32

RenderAtEndOf

0.31

Activations Density 1.053%

names of individuals involved in various interactions and activities

No Comments

No Known Activations