INDEX

Explanations

technical terms and declarations in code or technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 CALIFORNI

-0.83

CHREIB

-0.81

VERTISEMENT

-0.78

ratulations

-0.75

MERCIAL

-0.74

IFICATE

-0.74

 ERSITY

-0.72

 DOWNVOTE

-0.71

NOUNC

-0.71

 DEPOSITORY

-0.68

POSITIVE LOGITS

 spirituale

0.76

UN

0.75

 latine

0.72

NO

0.72

 naturali

0.72

 individuale

0.71

 universale

0.71

 ostrich

0.70

 poichè

0.70

ROE

0.69

Activations Density 2.287%

technical terms and declarations in code or technical specifications

No Comments

No Known Activations