INDEX

Explanations

specific nouns and scientific terms related to classification and analysis

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

achievements, variant, distinguished

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

Not in Any Lists

No Comments

Negative Logits

Geplaatst

-0.57

rawDesc

-0.53

Jeografia

-0.52

Vidite

-0.46

+:+

-0.41

 defStyle

-0.41

AlterField

-0.40

 kasarigan

-0.39

ьаж

-0.38

 GetEnumerator

-0.38

POSITIVE LOGITS

DIPSETTING

0.50

cshtml

0.49

 '\\;'

0.42

 peti

0.39

nodoc

0.38

 MyBatis

0.38

AndEndTag

0.36

 informée

0.36

AsStream

0.36

 Analysis

0.36

Activations Density 0.273%

specific nouns and scientific terms related to classification and analysis

achievements, variant, distinguished

No Comments

No Known Activations