INDEX

Explanations

mathematical expressions and notation

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

Code snippets with brackets and symbols

np_acts-logits-general · gemini-2.0-flash

integrals and function arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Baillargeon

-0.51

 Dead

-0.47

صف

-0.44

вав

-0.44

 newOwner

-0.43

offsetof

-0.42

multirow

-0.42

 HasFactory

-0.40

BROAD

-0.40

一次

-0.39

POSITIVE LOGITS

DockStyle

0.70

FontOfSize

0.69

 MotionEvent

0.68

 propOrder

0.68

 MainAxisSize

0.68

 Distances

0.64

 समीक्षक

0.63

 time

0.60

ConstraintMaker

0.59

 waktu

0.59

Activations Density 2.023%

mathematical expressions and notation

Code snippets with brackets and symbols

integrals and function arguments

No Comments

No Known Activations