INDEX

Explanations

terms related to applications, requests, and legal documents

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

 disambiguazione

-0.64

 téléchargez

-0.62

 '\\;'

-0.59

BeginInit

-0.59

aarrggbb

-0.58

ValueStyle

-0.56

 noqa

-0.54

ENESS

-0.54

borderSide

-0.54

empi

-0.54

POSITIVE LOGITS

 lodged

0.64

FormTagHelper

0.63

 placed

0.61

 submitted

0.60

 made

0.60

 dépos

0.57

jangkau

0.55

 gedaan

0.53

 requesting

0.52

 filed

0.51

Activations Density 0.499%

terms related to applications, requests, and legal documents

No Comments

No Known Activations