INDEX

Explanations

references to the word "Ju" or variations of it, likely related to a particular subject or context involving the term

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 NSCoder

-0.57

AddTagHelper

-0.54

Autoritní

-0.50

strokeWeight

-0.50

ChildScrollView

-0.49

 planètes

-0.49

oader

-0.48

oredCriteria

-0.46

GOTREF

-0.46

 handkerchief

-0.45

POSITIVE LOGITS

 архивлан

0.59

awaiter

0.55

__":

0.53

RepeatedField

0.51

 colspan

0.50

canestro

0.48

illiard

0.47

="@+

0.47

twimg

0.47

ventas

0.46

Activations Density 0.391%

references to the word "Ju" or variations of it, likely related to a particular subject or context involving the term

No Comments

No Known Activations