INDEX

Explanations

questions and discussions about the significance and implications of concepts

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

questions and explanations

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

hamos

-0.34

 tranqu

-0.33

 helicóptero

-0.32

 RemoteException

-0.32

 Príncipe

-0.30

 intima

-0.29

 aikaa

-0.29

 matters

-0.29

 изо

-0.29

{},

-0.28

POSITIVE LOGITS

 Administrativna

0.76

ftagPool

0.74

хьтан

0.67

addPreferredGap

0.61

 nahilalakip

0.60

IntoConstraints

0.60

rungsseite

0.59

 resourceCulture

0.58

Демографія

0.57

GTCX

0.57

Activations Density 0.070%

questions and discussions about the significance and implications of concepts

questions and explanations

No Comments

No Known Activations