INDEX

Explanations

structured formats and numbers within texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 préf

-0.57

 sauvages

-0.55

WebElementEntity

-0.55

 chère

-0.49

thoven

-0.48

ponents

-0.48

 fundamento

-0.47

 étn

-0.47

 Gesundheits

-0.46

 clés

-0.46

POSITIVE LOGITS

 ब्रेकडाउन

0.62

بوابة

0.58

SharedCtor

0.57

TabIndex

0.57

Collegamenti

0.57

MockMvc

0.56

enterOuterAlt

0.56

SBATCH

0.54

WriteTagHelper

0.53

 AttributeSet

0.53

Activations Density 0.288%

structured formats and numbers within texts

No Comments

No Known Activations