INDEX

Explanations

mentions of character encodings, specifically UTF formats

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.76

InitVars

-0.75

исленность

-0.73

 دیکھیے

-0.67

webElement

-0.67

IntoConstraints

-0.63

aarrggbb

-0.63

Jeografia

-0.62

TemporalType

-0.60

MergeFrom

-0.59

POSITIVE LOGITS

UTF

0.83

 FontWeight

0.80

styleable

0.64

enumi

0.64

PageIndex

0.64

KEYCODE

0.62

 CURLOPT

0.58

UTF

0.56

 OMITTED

0.55

ientí

0.53

Activations Density 0.018%

mentions of character encodings, specifically UTF formats

No Comments

No Known Activations