INDEX

Explanations

references to specific programming constructs or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 lenker

-0.69

RegressionTest

-0.63

grá

-0.62

?");

-0.59

EnableWeb

-0.57

gelöst

-0.57

ifest

-0.55

WAH

-0.55

SupportActionBar

-0.54

 المعيارى

-0.54

POSITIVE LOGITS

factory

0.63

aw

0.62

 financeiro

0.61

 klart

0.61

TypedDataSet

0.60

WithIOException

0.56

 متعلقه

0.55

AW

0.55

الحياه

0.55

mobileqq

0.54

Activations Density 0.174%

references to specific programming constructs or structures

No Comments

No Known Activations