INDEX

Explanations

references to specific authors and their works in the context of statistical literature

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

Robins' publications

np_acts-logits-general · gemini-2.0-flash

Robins

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

Personendaten

-0.66

 Charlemagne

-0.61

})`

-0.59

äsident

-0.56

 MainAxisSize

-0.55

lgari

-0.55

verläs

-0.55

BackPressed

-0.54

 tact

-0.54

\"");

-0.53

POSITIVE LOGITS

Rob

0.70

Rob

0.62

mathsf

0.58

 createSlice

0.57

 robar

0.57

ṣ

0.55

rob

0.55

ôs

0.55

rob

0.54

Manbalar

0.54

Activations Density 0.093%

references to specific authors and their works in the context of statistical literature

Robins' publications

Robins

No Comments

No Known Activations