INDEX

Explanations

code-related terminology and technical constructs

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

typeorm

-0.59

ViewFeatures

-0.57

InvalidProtocol

-0.53

resave

-0.52

ospel

-0.49

Accessors

-0.48

HasMaxLength

-0.47

rrggbb

-0.47

dith

-0.46

ost

-0.46

POSITIVE LOGITS

 localVar

0.61

 ModelExpression

0.61

ConstraintMaker

0.60

NameInMap

0.59

tvguidetime

0.58

ανά

0.56

 समीक्षाओं

0.54

Threat

0.53

]--;

0.52

swagger

0.52

Activations Density 0.215%

code-related terminology and technical constructs

No Comments

No Known Activations