INDEX

Explanations

programming language code snippets and structural elements related to libraries or frameworks

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

type definitions and declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

Personendaten

-0.91

 autorytatywna

-0.87

 ब्रेकडाउन

-0.71

expandindo

-0.69

 мәкал

-0.63

tanleria

-0.61

 Autorizaciones

-0.60

 typelib

-0.60

点此举报

-0.59

 Keuangan

-0.58

POSITIVE LOGITS

bra

0.39

 restless

0.38

 pitch

0.38

minecraftforge

0.38

EM

0.36

 stale

0.34

YB

0.33

ях

0.33

alsa

0.33

KM

0.32

Activations Density 0.002%

programming language code snippets and structural elements related to libraries or frameworks

type definitions and declarations

No Comments

No Known Activations