INDEX

Explanations

specific quantitative measures and terminologies related to scientific experiments and statistical outcomes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

quantities expressed with numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Negative Logits

-0.38

ۗ

-0.35

 laurent

-0.35

логи

-0.34

’

-0.34

-0.33

 amplific

-0.33

diens

-0.32

<em>

-0.32

Dir

-0.32

POSITIVE LOGITS

AddTagHelper

0.68

ValueStyle

0.63

 nahilalakip

0.62

 arşivlendi

0.61

Enllaços

0.60

Manbalar

0.59

ніципалі

0.58

WaitGroup

0.57

GenerationType

0.57

UpInside

0.57

Activations Density 0.055%

specific quantitative measures and terminologies related to scientific experiments and statistical outcomes

quantities expressed with numbers

No Known Activations