INDEX

Explanations

references to research methodology and evidence in scientific contexts

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

Hentet

-0.79

 Wikimédia

-0.63

ثيق

-0.52

BeginContext

-0.51

 AssemblyCompany

-0.49

 EconPapers

-0.47

chenken

-0.46

RTLU

-0.46

ém

-0.44

indd

-0.44

POSITIVE LOGITS

 Roskov

0.68

ibatis

0.67

ografija

0.60

FailureListener

0.59

iprot

0.56

NVIC

0.54

CompleteListener

0.53

الإنجليزية

0.53

 دیکھیے

0.52

DECREF

0.52

Activations Density 1.457%

references to research methodology and evidence in scientific contexts

No Comments

No Known Activations