INDEX

Explanations

formatted or structured information, particularly in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ReusableCell

-0.63

 kaarangay

-0.62

 getItemId

-0.56

 ویکی‌پدی

-0.55

OptionsMenu

-0.50

 Teufel

-0.47

Билгалдахарш

-0.47

botas

-0.46

 hẹn

-0.45

findall

-0.44

POSITIVE LOGITS

str

0.86

 Brecht

0.79

bra

0.78

Bra

0.77

Bra

0.77

itra

0.77

 Strat

0.75

tra

0.75

TRA

0.75

 Bradshaw

0.75

Activations Density 0.511%

formatted or structured information, particularly in scientific or technical contexts

No Comments

No Known Activations