INDEX

Explanations

symbols and formatting elements associated with computer code or markup

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

 procede

-0.52

ญิง

-0.42

 Espinosa

-0.41

 Donahue

-0.41

＾

-0.40

 Shakira

-0.40

流れ

-0.38

chá

-0.38

 Archivado

-0.38

 idéia

-0.37

POSITIVE LOGITS

CppMethod

0.90

ContentAsync

0.88

 ModelExpression

0.87

 Signalez

0.87

 resourceCulture

0.86

tvguidetime

0.85

########.

0.83

!*\

0.82

 HasFactory

0.82

">😂

0.79

Activations Density 0.062%

symbols and formatting elements associated with computer code or markup

No Comments

No Known Activations