INDEX

Explanations

proper nouns and significant identifiers, particularly names and locations

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

California, university, robins

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 سكانية

-0.57

 виправивши

-0.54

exitRule

-0.49

expandindo

-0.47

setVerticalGroup

-0.45

 برانيه

-0.45

iqué

-0.43

 الرياضيه

-0.43

 кӀ

-0.43

ISupport

-0.42

POSITIVE LOGITS

 незавершена

0.43

ValueStyle

0.42

 humanidade

0.42

 femininos

0.41

methoxy

0.39

OGND

0.38

 المعيارى

0.37

jsonwebtoken

0.36

ACHUSET

0.36

Referanser

0.35

Activations Density 0.000%

proper nouns and significant identifiers, particularly names and locations

California, university, robins

No Comments

No Known Activations