INDEX

Explanations

references to research, knowledge, or expertise related to topics of interest

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

elemField

-0.69

StructEnd

-0.67

ImageContext

-0.64

DeleteBehavior

-0.64

tvguidetime

-0.62

 <=",

-0.56

 مواليد

-0.56

 مرئيه

-0.55

bewerken

-0.54

 AssemblyVersion

-0.54

POSITIVE LOGITS

 observant

0.62

Anyone

0.61

бият

0.58

 Anyone

0.58

anyone

0.55

 Anybody

0.55

 glance

0.54

 anyone

0.53

都知道

0.53

Anybody

0.53

Activations Density 0.165%

references to research, knowledge, or expertise related to topics of interest

No Comments

No Known Activations