INDEX

Explanations

references to specific geographical locations or entities

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

laria

-0.59

征詢

-0.56

 כול

-0.55

 læng

-0.52

 Imperio

-0.52

">

-0.51

 препратки

-0.51

 Psicología

-0.50

-------------</

-0.49

ñola

-0.49

POSITIVE LOGITS

Se

0.77

Po

0.73

Ma

0.71

Re

0.69

Se

0.69

Te

0.68

Bi

0.68

Po

0.68

Ke

0.68

Re

0.67

Activations Density 0.861%

references to specific geographical locations or entities

No Comments

No Known Activations