INDEX

Explanations

technical references and keywords related to API documentation and programming languages

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

ValueStyle

-0.82

AccessorTable

-0.79

ThroughAttribute

-0.77

webElement

-0.75

AnchorStyles

-0.75

AndEndTag

-0.73

tagHelperRunner

-0.73

AsUp

-0.70

ViewFeatures

-0.69

Geplaatst

-0.68

POSITIVE LOGITS

Efq

0.72

بوابة

0.61

uskas

0.53

 Perſ

0.51

 ""));

0.51

ſelf

0.51

neth

0.49

 houſe

0.49

seits

0.49

łaszcza

0.48

Activations Density 0.563%

technical references and keywords related to API documentation and programming languages

No Comments

No Known Activations