INDEX

Explanations

programming constructs and data types related to threads and iterators

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

Data types or class names

np_acts-logits-general · gemini-2.0-flash

programmers declare variables

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ArgsConstructor

-0.68

 فريبيس

-0.66

\{\\

-0.65

 <=",

-0.65

 Shakspeare

-0.65

intios

-0.61

 NSCoder

-0.60

 Roskov

-0.59

 fubject

-0.58

ſelf

-0.57

POSITIVE LOGITS

 final

0.70

[]

0.66

 result

0.66

AnchorTagHelper

0.58

aux

0.56

 AssemblyProduct

0.56

new

0.56

########.

0.55

cas

0.54

con

0.54

Activations Density 0.100%

programming constructs and data types related to threads and iterators

Data types or class names

programmers declare variables

No Comments

No Known Activations