INDEX

Explanations

references to different layers in a structure or material

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinulongan

-0.82

MHD

-0.81

hlí

-0.81

DotNetBar

-0.80

)_/¯

-0.78

/**

-0.77

MemoryWarning

-0.76

 Constitucional

-0.76

xmlhttp

-0.75

Dixie

-0.75

POSITIVE LOGITS

 Layer

1.77

 Layers

1.75

 layers

1.73

 layer

1.71

 LAYER

1.68

Layers

1.65

Layer

1.61

layer

1.60

layers

1.53

LAYER

1.44

Activations Density 0.083%

references to different layers in a structure or material

No Comments

No Known Activations