INDEX

Explanations

words and terms related to scientific measurements and equipment

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

 تضيفلها

-0.68

orithmic

-0.65

lankton

-0.62

esticides

-0.59

습니다

-0.56

 című

-0.55

kespeare

-0.55

ьаж

-0.54

Zeneca

-0.54

quiel

-0.53

POSITIVE LOGITS

pia

0.66

awm

0.65

̍

0.65

IUrlHelper

0.63

 []).

0.63

DoubleQuotes

0.60

Nia

0.60

Fue

0.59

iai

0.59

stateProvider

0.58

Activations Density 0.323%

words and terms related to scientific measurements and equipment

No Comments

No Known Activations