INDEX

Explanations

programming constructs related to conditionals and error handling

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

Code-related terms and syntax

np_acts-logits-general · gemini-2.0-flash

symptoms are

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TintMode

-0.56

 Sucre

-0.51

userdetails

-0.46

SharedCtor

-0.46

ernsey

-0.46

windowFixed

-0.45

цездатний

-0.45

__*/

-0.44

 Wiktionnaire

-0.44

onViewCreated

-0.43

POSITIVE LOGITS

styleType

0.70

findpost

0.65

JMenuBar

0.64

CloseOperation

0.60

ніципалі

0.60

IsContent

0.55

migrationBuilder

0.53

CWE

0.53

BagConstraints

0.53

ájá

0.53

Activations Density 0.086%

programming constructs related to conditionals and error handling

Code-related terms and syntax

symptoms are

No Comments

No Known Activations