INDEX

Explanations

examples or illustrations of concepts or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

MessageOf

-0.76

GEBURTSDATUM

-0.73

MigrationBuilder

-0.68

featureID

-0.58

 입니다

-0.55

WithIOException

-0.55

 становника

-0.55

 korean

-0.53

 africaine

-0.53

PreferredItem

-0.53

POSITIVE LOGITS

PLANATION

0.56

たとえば

0.53

SequentialGroup

0.51

ẹo

0.48

subplots

0.48

 even

0.47

 particularly

0.47

中でも

0.45

inephrine

0.45

 especially

0.44

Activations Density 0.394%

examples or illustrations of concepts or arguments

No Comments

No Known Activations