INDEX

Explanations

characters or names from a specific narrative or story context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 وتسجيلات

-0.99

+:+

-0.99

MessageTagHelper

-0.98

Efq

-0.96

 JpaRepository

-0.91

VersionUID

-0.89

 محفوظة

-0.83

IsMutable

-0.81

CopyWith

-0.81

});*/

-0.81

POSITIVE LOGITS

lie

0.44

 mergeFrom

0.44

 trans

0.42

 range

0.42

ому

0.40

die

0.39

EnumMember

0.38

trans

0.38

ta

0.38

Cha

0.38

Activations Density 0.149%

characters or names from a specific narrative or story context

No Comments

No Known Activations