INDEX

Explanations

references to academic papers and publishing information

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

 propOrder

-0.88

AndroidJUnit

-0.73

+#+#

-0.68

 ComVisible

-0.67

ngdoc

-0.67

StoryboardSegue

-0.66

 JpaRepository

-0.65

WebServlet

-0.64

rungsseite

-0.64

 CURLOPT

-0.64

POSITIVE LOGITS

eração

0.51

tsch

0.50

 Betten

0.47

arb

0.47

sify

0.46

 Ponta

0.45

ալ

0.45

 stenosis

0.43

otomy

0.43

 Official

0.43

Activations Density 0.333%

references to academic papers and publishing information

No Comments

No Known Activations