INDEX

Explanations

references to panels or discussions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/),

-0.74

SRR

-0.73

shaders

-0.71

ificantly

-0.68

 Fortaleza

-0.68

>-->

-0.67

']?>

-0.67

 HttpResponse

-0.66

 dece

-0.66

dication

-0.65

POSITIVE LOGITS

 panels

1.65

 panel

1.58

 Panel

1.56

panel

1.51

panels

1.50

 Panels

1.48

Panel

1.46

Panels

1.40

 PANEL

1.39

PANEL

1.37

Activations Density 0.066%

references to panels or discussions

No Comments

No Known Activations