INDEX

Explanations

references to specific metrics or identities related to performance or evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

HomeComponent

-0.47

-0.46

ham

-0.43

Configurable

-0.43

発

-0.42

gaande

-0.42

тое

-0.41

Inc

-0.41

 incident

-0.41

corr

-0.40

POSITIVE LOGITS

XMLSchema

1.00

 wireType

0.97

 ModelExpression

0.88

abetes

0.86

MigrationBuilder

0.85

]='\

0.81

تقاوى

0.78

PerformLayout

0.78

 TextInputType

0.78

complexType

0.76

Activations Density 0.442%

references to specific metrics or identities related to performance or evaluation

No Comments

No Known Activations