INDEX

Explanations

mathematical symbols and expressions related to relationships between variables in formal logic and set theory

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

relation definition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MessageTagHelper

-0.54

новништво

-0.52

AxisAlignment

-0.52

featureID

-0.52

DotNetBar

-0.52

 AssemblyCulture

-0.51

 Materia

-0.51

Bibitem

-0.51

UnusedPrivate

-0.50

parsedMessage

-0.49

POSITIVE LOGITS

ngrx

0.38

 للاسماء

0.36

通

0.32

exists

0.32

pat

0.31

 Thru

0.30

Bernhard

0.30

通

0.30

Personendaten

0.29

 transitive

0.29

Activations Density 0.151%

mathematical symbols and expressions related to relationships between variables in formal logic and set theory

relation definition

No Comments

No Known Activations