INDEX

Explanations

names of people or references to authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

verket

-0.68

 étranger

-0.63

numerusform

-0.62

 algemeen

-0.60

 extérieurs

-0.60

 تانيه

-0.59

COUVER

-0.58

APORE

-0.58

 OnInit

-0.58

 épis

-0.56

POSITIVE LOGITS

Lugares

0.60

DbType

0.59

 Sack

0.59

ofire

0.59

Mad

0.55

ofday

0.54

ThroughAttribute

0.53

 Fili

0.53

 turtleneck

0.53

 DbType

0.53

Activations Density 0.200%

names of people or references to authors

No Comments

No Known Activations