INDEX

Explanations

phrases indicating user actions or interactions within a digital context

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

common function tokens (short connectors like conjunctions/prepositions) and miscellaneous symbols/formatting marks, especially in technical or mathematical contexts.

oai_token-act-pair · gpt-5 Triggered by @timna

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

⋙

-0.52

erdings

-0.44

mds

-0.42

 cortas

-0.41

 bestemt

-0.38

 olev

-0.38

þe

-0.38

cluye

-0.37

 planas

-0.37

epy

-0.37

POSITIVE LOGITS

 AssemblyCulture

1.19

WithIOException

1.18

LookAnd

1.17

DebuggerNonUser

1.06

 kasarigan

1.01

 defaultstate

1.00

rungsseite

0.99

 propOrder

0.97

NameInMap

0.94

MigrationBuilder

0.93

Activations Density 0.193%

phrases indicating user actions or interactions within a digital context

common function tokens (short connectors like conjunctions/prepositions) and miscellaneous symbols/formatting marks, especially in technical or mathematical contexts.

No Comments

No Known Activations