INDEX

Explanations

terms related to vertices and edges in graph theory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

farin

-0.85

 NSCoder

-0.85

 snippetHide

-0.85

 Exacts

-0.82

Filmographie

-0.82

Diwedd

-0.79

MeasureSpec

-0.77

 NSMutable

-0.76

-0.73

 &___

-0.73

POSITIVE LOGITS

 vertices

1.65

 vertex

1.59

vertices

1.43

vertex

1.39

Vertex

1.32

 Vertex

1.32

Vertices

1.24

 VERT

0.93

VERTEX

0.92

addVertex

0.85

Activations Density 0.092%

terms related to vertices and edges in graph theory

No Comments

No Known Activations