INDEX

Explanations

terminology related to enhancements or modifications in processes or systems

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

 oamen

-0.60

 tuturor

-0.56

 löytyy

-0.54

 oameni

-0.53

 angelegt

-0.52

 acrylique

-0.49

 ferdig

-0.49

 geweest

-0.48

 skjø

-0.48

 bygget

-0.48

POSITIVE LOGITS

 betweenstory

0.76

 NSCoder

0.65

featureID

0.63

AddTagHelper

0.62

 snippetHide

0.62

 gradually

0.61

KommentareTeilen

0.60

 improved

0.59

 upgraded

0.57

createCell

0.56

Activations Density 0.985%

terminology related to enhancements or modifications in processes or systems

No Comments

No Known Activations