INDEX

Explanations

references to legal or procedural terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 activer

-0.50

 ActionResult

-0.46

 EventArgs

-0.46

ArgumentParser

-0.42

GRANTED

-0.42

Cancelar

-0.42

tm

-0.41

PyExc

-0.41

leiding

-0.41

ის

-0.40

POSITIVE LOGITS

Tikang

0.86

 تضيفلها

0.85

Tembelea

0.73

MigrationBuilder

0.72

ConstraintMaker

0.71

 EconPapers

0.71

verwijspagina

0.66

 nakalista

0.65

EDEFAULT

0.65

 transfieras

0.65

Activations Density 0.923%

references to legal or procedural terminology

No Comments

No Known Activations