INDEX

Explanations

terms related to layers in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

/**

-0.94

MHD

-0.88

 maș

-0.87

DotNetBar

-0.87

WriteBarrier

-0.86

 weevil

-0.86

hlí

-0.85

StoryboardSegue

-0.85

 Roskov

-0.84

 تانيه

-0.83

POSITIVE LOGITS

 Layer

1.92

 layer

1.90

 layers

1.88

 Layers

1.84

 LAYER

1.79

Layer

1.74

layer

1.71

Layers

1.69

layers

1.58

LAYER

1.50

Activations Density 0.065%

terms related to layers in a structured context

No Comments

No Known Activations