INDEX

Explanations

numerical data and references to statistics or measurements

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

Tokens followed by numbers

np_acts-logits-general · gemini-2.0-flash

numbers and mathematical notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

исленность

-0.86

 pulumi

-0.72

 SafeMath

-0.59

 оригіналу

-0.59

Rhestr

-0.58

 helyez

-0.56

下载附件

-0.56

addGap

-0.55

 ProtoMessage

-0.55

раздо

-0.54

POSITIVE LOGITS

0.77

 thirteen

0.75

0.73

 Thirteen

0.70

 eight

0.69

 nine

0.68

 fourteen

0.68

 seventeen

0.66

Activations Density 2.340%

numerical data and references to statistics or measurements

Tokens followed by numbers

numbers and mathematical notation

No Comments

No Known Activations