INDEX

Explanations

code sections and related technical terms in programming or API documentation

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

cla

-0.53

 cửa

-0.50

ift

-0.48

akes

-0.48

 détruire

-0.47

исленность

-0.47

chend

-0.45

 NavController

-0.45

odu

-0.45

POSITIVE LOGITS

enschappelijke

0.68

 feminina

0.64

Personensuche

0.64

 Nymp

0.58

dicionado

0.58

 ReSharper

0.58

*{

0.57

Juf

0.56

{@

0.56

 Sarm

0.55

Activations Density 0.022%

code sections and related technical terms in programming or API documentation

No Comments

No Known Activations