INDEX

Explanations

numerical data, particularly related to statistics and measurements

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

rem

-0.49

 termes

-0.41

 enfance

-0.41

 désigne

-0.40

 superiori

-0.40

ције

-0.39

 iniciales

-0.39

 supérieures

-0.38

 popolari

-0.38

 ennemis

-0.38

POSITIVE LOGITS

 MainAxisSize

0.85

 PyTuple

0.83

 viewType

0.82

Efq

0.82

 Chwiliwch

0.81

 MotionEvent

0.79

 ModelExpression

0.77

FontOfSize

0.76

 GenerationType

0.76

 CreateTagHelper

0.75

Activations Density 0.393%

numerical data, particularly related to statistics and measurements

No Comments

No Known Activations