INDEX

Explanations

structure and definitions of properties and classes in code

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

get get

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

AISSEE

-0.65

styleType

-0.65

évaluateur

-0.64

 kaarangay

-0.64

 ſche

-0.63

 queſta

-0.60



-0.59

دانشنامهٔ

-0.58

 queſto

-0.58

 OMITBAD

-0.56

POSITIVE LOGITS

ValueGenerated

0.50

setVerticalGroup

0.45

 ExecuteAsync

0.35

standig

0.34

Erstellt

0.34

texttt

0.31

 regenerated

0.31



0.30

ACTERS

0.29

Filmografie

0.29

Activations Density 0.005%

structure and definitions of properties and classes in code

get get

No Comments

No Known Activations