INDEX

Explanations

items related to documentation, including sections and proofs in a formal paper

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

Q.E.D. or Box

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 متعلقه

-0.43

 riten

-0.37

ConstraintMaker

-0.36

▻

-0.35

һы

-0.35

 ligiloj

-0.34

SqlSession

-0.34

InitStruct

-0.33

 محفوظة

-0.33

 JADX

-0.33

POSITIVE LOGITS

 nakalista

0.75

bewerken

0.67



0.64

 Italijanski

0.62

 дописавши

0.61

 getItemCount

0.59

 disambiguazione

0.58

 nahilalakip

0.56

endpush

0.55

LookAnd

0.54

Activations Density 0.030%

items related to documentation, including sections and proofs in a formal paper

Q.E.D. or Box

No Comments

No Known Activations