INDEX

Explanations

references to records and official documentation

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

official listings and records

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

 movilidad

-0.39

CDCl

-0.36

 trasladado

-0.36

 adopción

-0.36

writeFieldEnd

-0.35

 suffit

-0.35

 heapq

-0.34

velocity

-0.34

 motion

-0.34

 productividad

-0.33

POSITIVE LOGITS

 propOrder

0.79

 nakalista

0.76

 autorytatywna

0.60

 AssemblyVersion

0.58

 Normdatei

0.55

 生命周期

0.52

 disambiguazione

0.51

хьтан

0.50

Autoritní

0.47

endsection

0.46

Activations Density 0.046%

references to records and official documentation

official listings and records

No Comments

No Known Activations