INDEX

Explanations

technical specifications related to content types and character encoding in data formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Autoritní

-0.58

 externi

-0.55

glGen

-0.51

 lenker

-0.49

 kasarigan

-0.48

ocuk

-0.47

 drone

-0.46

 ModelExpression

-0.46

ItemGroup

-0.46

BoxShadow

-0.46

POSITIVE LOGITS

UTF

0.92

utf

0.90

utf

0.89

UTF

0.88

 charset

0.83

 encoding

0.78

Encoding

0.78

 Encoding

0.78

Utf

0.73

charset

0.71

Activations Density 0.288%

technical specifications related to content types and character encoding in data formats

No Comments

No Known Activations