INDEX

Explanations

references to specific research entities or measurements in scientific literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 historical

-0.82

Historical

-0.76

historical

-0.73

 historic

-0.62

horizontal

-0.59

 histórica

-0.58

 homologous

-0.57

 historique

-0.56

 honorary

-0.56

 heritage

-0.56

POSITIVE LOGITS

bootstrapcdn

0.69

 pylori

0.67

AutoField

0.65

OGND

0.62

principalTable

0.60

TintMode

0.60

SourceChecksum

0.59

 sapiens

0.58

actylus

0.58

AppCompat

0.55

Activations Density 0.931%

references to specific research entities or measurements in scientific literature

No Comments

No Known Activations