INDEX

Explanations

references to estimators and statistical methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

expandindo

-0.59

 Instantly

-0.45

isContained

-0.45

 graded

-0.44

örder

-0.44

 ninguém

-0.43

 grade

-0.43

dev

-0.43

 Revolutionary

-0.42

kende

-0.42

POSITIVE LOGITS

 Normdatei

0.80

Jereo

0.69

 يتيمه

0.69

WebVitals

0.67

matchCondition

0.67

BeginContext

0.64

 تضيفلها

0.63

Naissance

0.61

onucleotide

0.60

findpost

0.59

Activations Density 0.657%

references to estimators and statistical methodologies

No Comments

No Known Activations