INDEX

Explanations

formatted code structures and specific programming patterns

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Мексичка

-1.01

QMetaType

-0.81

Ecotoxicity

-0.77

Abitanti

-0.77

ronpa

-0.76

irq

-0.74

 itſelf

-0.73

writeFieldEnd

-0.73

 doInBackground

-0.72

IRQ

-0.69

POSITIVE LOGITS

0.58

hagen

0.58

“

0.56

Ser

0.54

*{\

0.54

0.53

 ModelExpression

0.53

 some

0.53

 faced

0.53

raise

0.53

Activations Density 0.070%

formatted code structures and specific programming patterns

No Comments

No Known Activations