INDEX

Explanations

references to official documents or sources

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enumi

-0.71

 שוליים

-0.70

expandindo

-0.67

enumii

-0.66

évaluateur

-0.66

 Paix

-0.63

 surla

-0.61

writeField

-0.61

 CreateTagHelper

-0.58

 célèbres

-0.58

POSITIVE LOGITS

dom

0.81

OFFICIAL

0.68

 sanctioned

0.67

izzate

0.65

ization

0.64

적으로

0.63

tiary

0.63

 OFFICIAL

0.62

dehy

0.62

initializeApp

0.61

Activations Density 0.053%

references to official documents or sources

No Comments

No Known Activations