INDEX

Explanations

cooking instructions and temperature settings

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

heating and cooking states

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

исленность

-0.55

requent

-0.51

oare

-0.49

ChildScrollView

-0.49

rungsseite

-0.47

aarrggbb

-0.46

 casts

-0.45

 informée

-0.45

 DPRD

-0.45

RefNanny

-0.44

POSITIVE LOGITS

 <=",

0.62

 snippetHide

0.54

RegistryLite

0.43

sizeCache

0.40

 kasarigan

0.38

 TestBed

0.38

=$?

0.34

outSlope

0.34

cessite

0.34

="../

0.33

Activations Density 0.006%

cooking instructions and temperature settings

heating and cooking states

No Comments

No Known Activations