INDEX

Explanations

references to specific metrics or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ChildScrollView

-0.92

 OFDb

-0.85

 HasFactory

-0.83

 Theſe

-0.76

ercito

-0.76

 MainAxisSize

-0.76

(!__

-0.75

 umani

-0.75

 DELLE

-0.75

GraphicsUnit

-0.74

POSITIVE LOGITS

 POINT

1.67

 point

1.58

 points

1.55

 Point

1.53

point

1.51

POINT

1.49

Point

1.40

 Points

1.39

points

1.37

 POINTS

1.37

Activations Density 0.093%

references to specific metrics or measurements

No Comments

No Known Activations