INDEX

Explanations

references to patents or licensing

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

 BoxFit

-0.61

KEYCODE

-0.52

FunctionFlags

-0.52

 MainAxisSize

-0.50

etak

-0.49

 minOccurs

-0.48

 поту

-0.47

#%

-0.47

 suporta

-0.47

 élèves

-0.47

POSITIVE LOGITS

USP

2.72

USP

1.80

허

1.70

原始内容存档于

1.17

 autorytatywna

0.97

usp

0.90

 jScrollPane

0.85

참고

0.73

 kasarigan

0.73

rungsseite

0.70

Activations Density 0.006%

references to patents or licensing

No Comments

No Known Activations