INDEX

Explanations

code snippets or elements related to programming syntax and declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

킬

-0.45

-0.44

nloa

-0.43

总体

-0.43

*/),

-0.43

Ever

-0.42

InjectMocks

-0.42

and

-0.41

POSITIVE LOGITS

 مرئيه

0.74

Altern

0.69

 alternatively

0.66

findpost

0.66

 alternatif

0.64

 Altern

0.64

 فريبيس

0.64

verwijspagina

0.63

antaranya

0.62

ilets

0.62

Activations Density 1.220%

code snippets or elements related to programming syntax and declarations

No Comments

No Known Activations