INDEX

Explanations

mathematical symbols and expressions related to propositions, assumptions, and proofs in a formal context

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

Punctuation followed by discourse markers

np_acts-logits-general · gemini-2.0-flash

conclusion from symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 itſelf

-0.72

 PublicKey

-0.62

 greateſt

-0.62

CPtr

-0.60

WebMethod

-0.59

WriteAttribute

-0.58

 Theſe

-0.57

venske

-0.57

 myſelf

-0.57

 palli

-0.57

POSITIVE LOGITS

 conclude

0.73

 conclure

0.66

 conclu

0.65

by

0.65

suy

0.64

 whence

0.62

 lại

0.61

又

0.60

 concluir

0.60

 since

0.58

Activations Density 1.092%

mathematical symbols and expressions related to propositions, assumptions, and proofs in a formal context

Punctuation followed by discourse markers

conclusion from symbols

No Comments

No Known Activations