INDEX

Explanations

references to various institutes and institutions

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

 clim

-0.77

Skocz

-0.75

ToMany

-0.73

Mâ

-0.72

CARBON

-0.71

pexpr

-0.70

hynch

-0.69

 Kraw

-0.69

Suz

-0.67

 senz

-0.66

POSITIVE LOGITS

 Institute

1.71

 institutes

1.56

 institute

1.52

Institute

1.51

 Institutes

1.48

 INSTITUTE

1.39

institute

1.35

 Institut

1.02

 instituto

1.02

Institut

0.98

Activations Density 0.010%

references to various institutes and institutions

No Comments

No Known Activations