INDEX

Explanations

specific identifiers or classifications 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 @ 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

LayoutManager

-0.96

er

-0.91

 Arian

-0.83

 MainAxisSize

-0.79

addContainerGap

-0.74

OGND

-0.74

args

-0.70

JSONException

-0.69

 gången

-0.69

rophes

-0.69

POSITIVE LOGITS

Mort

1.07

 Mort

0.92

 Mord

0.86

 Prima

0.81

 Rendez

0.77

 bist

0.77

 tund

0.77

 Blom

0.76

Mord

0.75

ORD

0.75

Activations Density 0.870%

specific identifiers or classifications in scientific or technical contexts

No Comments

No Known Activations