INDEX

Explanations

mathematical symbols and notations in a technical context

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

programming syntax and values

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 NSCoder

-0.48

SourceChecksum

-0.45

InSection

-0.44

webElementGuid

-0.44

Życiorys

-0.43

UnknownFieldSet

-0.43

 étanche

-0.40

 gepubliceerd

-0.39

parsedMessage

-0.38

ModelAdmin

-0.38

POSITIVE LOGITS



0.51

bootstrapcdn

0.49

abetes

0.45

 linkovi

0.43

DeleteMapping

0.41

PyExc

0.41

 للاسماء

0.39

XmlAccessType

0.39

]=>

0.38

Activations Density 0.002%

mathematical symbols and notations in a technical context

programming syntax and values

No Comments

No Known Activations