INDEX

Explanations

programming and technical terms related to data structures and document handling

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.73

AsUp

-0.66

WriteTagHelper

-0.64

Hochspringen

-0.62

 CreateTagHelper

-0.62

 NSCoder

-0.60

MemoryWarning

-0.60

 tartalomajánló

-0.60

 jspb

-0.58

 SEDS

-0.58

POSITIVE LOGITS

jButton

0.55

Cu

0.52

 semej

0.49

Toolbar

0.48

ToolStrip

0.48

toContain

0.47

 Toolbar

0.47

featureID

0.46

Cu

0.46

honey

0.46

Activations Density 2.555%

programming and technical terms related to data structures and document handling

No Comments

No Known Activations