INDEX

Explanations

references to studies, methods, or patterns in research papers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UrlResolution

-0.71

ingeki

-0.64

Espèce

-0.63

-/**

-0.61

+/**

-0.58

 localObject

-0.57

ínsula

-0.54

Filmo

-0.53

trauer

-0.53

 bậc

-0.53

POSITIVE LOGITS

 "..\..\

0.60

@"/

0.57

年

0.56

 <>",

0.55

 gepubliceerd

0.55

 OFDb

0.53

 onwards

0.53

 "..\..\..\

0.53

wnia

0.51

 regolare

0.51

Activations Density 0.896%

references to studies, methods, or patterns in research papers

No Comments

No Known Activations