INDEX

Explanations

instances of codes or identifiers in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

RegressionTest

-0.72

}{@

-0.65

 kaarangay

-0.59

parsedMessage

-0.57

 للمعارف

-0.57

 handleMessage

-0.55

çamento

-0.54

 them

-0.52

Viitteet

-0.51

transQ

-0.51

POSITIVE LOGITS

 BoxFit

0.57

dede

0.53

abad

0.53

₁,

0.51

DataAnnotations

0.51

ed

0.51

DED

0.48

ABAD

0.48

/***/

0.46

edly

0.46

Activations Density 0.180%

instances of codes or identifiers in a structured format

No Comments

No Known Activations