INDEX

Explanations

mathematical notation and terms used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Paglinawan

-0.67

Diweddarwch

-0.67

 }^{[

-0.59

 فريبيس

-0.57

loadAll

-0.57

semp

-0.57

mpä

-0.56

 ***!

-0.56

Demografia

-0.55

Aiheesta

-0.55

POSITIVE LOGITS

 biografias

0.62

 disparu

0.60

 <=",

0.59

schedulers

0.56

guien

0.55

 isolé

0.55

thenReturn

0.53

 tué

0.52

 religieuses

0.52

 battre

0.51

Activations Density 1.539%

mathematical notation and terms used in equations

No Comments

No Known Activations