INDEX

Explanations

specific names and proper nouns

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

Incomplete or misspelled words

np_acts-logits-general · gemini-2.0-flash

common word endings

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

tvguidetime

-0.49

pædia

-0.47

 tikra

-0.45

 vrijwilli

-0.45

-0.44

ICIA

-0.42

 McAllister

-0.42

 practically

-0.42

your

-0.41

Todavía

-0.41

POSITIVE LOGITS

AxisAlignment

0.61

InteropServices

0.56

AnimationsModule

0.52

Personendaten

0.50

InitVars

0.49

 BoxFit

0.47

oa̍t

0.47

saraba

0.47

IsContent

0.47

Diwedd

0.46

Activations Density 1.187%

specific names and proper nouns

Incomplete or misspelled words

common word endings

No Comments

No Known Activations