INDEX

Explanations

information related to data analysis and results reporting within studies

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

"Data" followed by a verb

np_acts-logits-general · gemini-2.0-flash

data collected or analyzed

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagHelper

-0.72

 resourceCulture

-0.64

 transfieras

-0.63

SourceChecksum

-0.63

AddTagHelper

-0.56

 Signalez

-0.55

 /\.(

-0.53

риев

-0.53

Named

-0.52

reportWebVitals

-0.51

POSITIVE LOGITS

 collected

1.16

 gathered

1.13

 gathering

0.95

collected

0.90

 obtained

0.85

 compiled

0.84

gathered

0.83

gathering

0.82

 gather

0.80

 Gathering

0.79

Activations Density 0.564%

information related to data analysis and results reporting within studies

"Data" followed by a verb

data collected or analyzed

No Comments

No Known Activations