INDEX

Explanations

numeric values, specifically those related to statistical measures or ratings

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

Values with margin of error

np_acts-logits-general · gemini-2.0-flash

numbers followed by parentheses

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

expandindo

-1.10

 ExecuteAsync

-1.04

 doubtnut

-0.95

 ostavi

-0.90

ьаж

-0.88

 resourceCulture

-0.87

GEBURTSDATUM

-0.87

 linkovi

-0.84

$_(

-0.83

 myſelf

-0.83

POSITIVE LOGITS

1.03

0.66

0.64

0.63

0.62

0.61

0.60

sa

0.60

Activations Density 0.486%

numeric values, specifically those related to statistical measures or ratings

Values with margin of error

numbers followed by parentheses

No Comments

No Known Activations