INDEX

Explanations

programming-related keywords and elements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

sizeCache

-0.82

AddHtmlAttribute

-0.76

 Мексичка

-0.66

 thicken

-0.63

PreferredItem

-0.63

LayoutStyle

-0.63

 kasarigan

-0.61

Personendaten

-0.60

InSection

-0.58

RegressionTest

-0.57

POSITIVE LOGITS

ScopeManager

0.74

ibatis

0.73

TagHelpers

0.63

 StatefulWidget

0.55

complexContent

0.54

 note

0.53

NullException

0.52

ambil

0.49

note

0.49

nologue

0.49

Activations Density 0.007%

programming-related keywords and elements in code

No Comments

No Known Activations