INDEX

Explanations

elements related to error handling and definitions within a code context

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

Code-related abbreviations/jargon

np_acts-logits-general · gemini-2.0-flash

code and macro definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Мексичка

-0.90

 '\\;'

-0.74

Personendaten

-0.70

migrationBuilder

-0.68

 Vikipedi

-0.66

Controllo

-0.66

bootstrapcdn

-0.65

 unknownFields

-0.65

Notae

-0.65

 HasFactory

-0.64

POSITIVE LOGITS

Â

0.56

TagMode

0.54

$.\\

0.47

tonode

0.47

â

0.46

AddHtmlAttribute

0.46

â

0.45

לוס

0.45

 eleg

0.44

>>>

0.44

Activations Density 0.645%

elements related to error handling and definitions within a code context

Code-related abbreviations/jargon

code and macro definitions

No Comments

No Known Activations