INDEX

Explanations

structured data types or programming syntax related to coding frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

canActivate

-0.60

enterOuterAlt

-0.59

setVerticalGroup

-0.58

 parseFrom

-0.53

EndGlobalSection

-0.51

 oprot

-0.51

 noDo

-0.49

tisgarh

-0.49

 createState

-0.49

AutoScaleMode

-0.48

POSITIVE LOGITS

 للمعارف

0.71

出版年

0.67

󠁢

0.67

 Preventive

0.62

OrNil

0.62

DotNetBar

0.56

 obec

0.56

enumi

0.55

Πηγές

0.54

stwie

0.53

Activations Density 0.029%

structured data types or programming syntax related to coding frameworks

No Comments

No Known Activations