INDEX

Explanations

a variety of data structure representations

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

Code snippets and technical jargon

np_acts-logits-general · gemini-2.0-flash

in + preposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ciatore

-0.64

localctx

-0.55

خاذ

-0.50

édez

-0.50

 BorderSide

-0.50

 bezeichneter

-0.49

chargeable

-0.48

RegistryLite

-0.48

Avez

-0.47

TacToe

-0.47

POSITIVE LOGITS

 Harian

0.53

{"

0.47

 varit

0.47

jnych

0.46

 adipis

0.45

{'

0.44

 disponibilités

0.44

volve

0.42

IconModule

0.42

 MemoryStream

0.41

Activations Density 0.115%

a variety of data structure representations

Code snippets and technical jargon

in + preposition

No Comments

No Known Activations