INDEX

Explanations

programming terminology and structure in technical documents

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eynman

-0.61

%</

-0.58

 betweenstory

-0.52

disposing

-0.52

Spoljašnje

-0.52

 otomatig

-0.51

retung

-0.51

 دیکھیے

-0.50

 endforeach

-0.49

ueba

-0.48

POSITIVE LOGITS

FontStyle

5.23

fontStyle

0.97

 nakalista

0.88

脚注の使い方

0.84

styleType

0.80

CellStyle

0.80

AnchorStyles

0.78

Hochspringen

0.77

 resourceCulture

0.77

 FontWeight

0.76

Activations Density 0.004%

programming terminology and structure in technical documents

No Comments

No Known Activations