INDEX

Explanations

references to specific geographic populations or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

WebServlet

-0.61

ReusableCell

-0.59

ATEGORY

-0.59

RTLD

-0.57

LLocation

-0.54

tagHelperRunner

-0.52

ఔ

-0.52

phemy

-0.51

 llamo

-0.50

 nonatomic

-0.50

POSITIVE LOGITS

 deposits

0.73

 deposit

0.66

 Formación

0.64

 beds

0.60

 facie

0.59

 DEPOSIT

0.58

 Formation

0.57

 formation

0.56

 layers

0.55

 locali

0.55

Activations Density 0.182%

references to specific geographic populations or locations

No Comments

No Known Activations