INDEX

Explanations

references to flow and flow-related charts or diagrams

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

"Flow" followed by a specific term

np_acts-logits-general · gemini-2.0-flash

flow chart, cytometry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 насељу

-0.76

 BoxFit

-0.76

jboss

-0.69

 MainAxisSize

-0.65

 flint

-0.62

'}';

-0.62

GoogleApiClient

-0.61

 onCancelled

-0.60

hnia

-0.60

 trasparente

-0.59

POSITIVE LOGITS

 flows

0.85

FLOW

0.84

 FLOW

0.80

 Flow

0.79

 cytometry

0.78

 Flows

0.76

flow

0.75

Flows

0.74

Flow

0.71

flows

0.71

Activations Density 0.121%

references to flow and flow-related charts or diagrams

"Flow" followed by a specific term

flow chart, cytometry

No Comments

No Known Activations