INDEX

Explanations

references to colors, primarily focusing on variants of white

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

LError

-0.62

 Leck

-0.60

 Journeys

-0.59

decade

-0.59

 Lend

-0.59

ScopeManager

-0.58

 ويكيپيديا

-0.58

edip

-0.56

relationship

-0.56

 Leap

-0.55

POSITIVE LOGITS

White

1.15

 Putih

1.14

 White

1.14

 white

1.04

white

1.04

 WHITE

1.02

WHITE

0.98

 Whites

0.87

Whites

0.84

 whites

0.82

Activations Density 0.117%

references to colors, primarily focusing on variants of white

No Comments

No Known Activations