INDEX

Explanations

references to formal notations or structural elements within technical or scientific texts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

يميديا

-0.85

CppCodeGen

-0.79

GEBURTSDATUM

-0.78

AsUp

-0.71

,‎

-0.70

')"

-0.67

::::::::

-0.66

 beginnetje

-0.66

ViewFeatures

-0.66

parsedMessage

-0.66

POSITIVE LOGITS

0.85

0.82

0.81

0.78

0.76

iyle

0.76

 idéia

0.73

0.71

Activations Density 0.135%

references to formal notations or structural elements within technical or scientific texts

No Comments

No Known Activations