INDEX

Explanations

code-related structures and elements in programming syntax

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

Graph-related terms and symbols

np_acts-logits-general · gemini-2.0-flash

graph connectivity and nodes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

cro

-0.47

unhofer

-0.47

 pitched

-0.46

ピ

-0.45

Cro

-0.45

,:,

-0.44

setPosition

-0.44

Cro

-0.44

 kombiniert

-0.44

cro

-0.43

POSITIVE LOGITS

 vertices

0.83

 nodes

0.79

 adjacency

0.79

fromnode

0.77

 Nodes

0.77

 Connectivity

0.75

 subgraph

0.75

jacency

0.73

 getNode

0.73

Connectivity

0.73

Activations Density 1.332%

code-related structures and elements in programming syntax

Graph-related terms and symbols

graph connectivity and nodes

No Comments

No Known Activations