INDEX

Explanations

terms related to mathematical proofs and theoretical frameworks

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

WebServlet

-0.76

 فريبيس

-0.70

)++;

-0.69

 Мексичка

-0.68

BeginContext

-0.67

tonsoft

-0.66

[*]

-0.66

zzleHttp

-0.64

OrNil

-0.64

Према

-0.63

POSITIVE LOGITS

izarse

0.45

 effective

0.40

its

0.40

 slutt

0.39

gdx

0.37

ori

0.37

 ordinaria

0.37

Forums

0.37

stoj

0.36

 externi

0.36

Activations Density 0.454%

terms related to mathematical proofs and theoretical frameworks

No Comments

No Known Activations