INDEX

Explanations

references to additional information or examples

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

The token "etc" followed by punctuation

np_acts-logits-general · gemini-2.0-flash

etc at end of list

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

\{\\

-0.71

*/

-0.67

 насељу

-0.66

"]);

-0.65

">—

-0.64

metry

-0.63

 كومونز

-0.62

 transfieras

-0.62

-0.60

 Stande

-0.59

POSITIVE LOGITS

etera

1.35

etc

0.83

ETC

0.76

etc

0.72

ETC

0.70

.,

0.68

曖昧さ回避

0.64

Etc

0.61

ništ

0.60

Etc

0.60

Activations Density 0.056%

references to additional information or examples

The token "etc" followed by punctuation

etc at end of list

No Comments

No Known Activations