INDEX

Explanations

programming-related terminology and structures, specifically in the context of Go language code

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

code: function calls and variable declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 ब्रेकडाउन

-0.41

intios

-0.40

неопр

-0.36

évaluateur

-0.35

 rond

-0.33

<?

-0.33

 dolayı

-0.33

 Vorder

-0.33

Rüyada

-0.32

 dynamic

-0.32

POSITIVE LOGITS

 protoimpl

0.62

protoimpl

0.60

UnsafeEnabled

0.58

 ProtoMessage

0.55

 '\\;'

0.54

 iNdEx

0.53

 NavController

0.53

AuxInt

0.53

tangentMode

0.51

TryDecodeAsNil

0.51

Activations Density 0.316%

programming-related terminology and structures, specifically in the context of Go language code

code: function calls and variable declarations

No Comments

No Known Activations