INDEX

Explanations

references to relationships and interactions between entities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hada

-0.50

 autorytatywna

-0.50

 مواليد

-0.49

 Stork

-0.48

ecore

-0.46

MENAFN

-0.46

findpost

-0.46

VersionUID

-0.46

luv

-0.44

ra

-0.44

POSITIVE LOGITS

 >=",

0.67

 AssemblyCulture

0.65

 /\.(

0.60

 invokingState

0.58

AnchorTagHelper

0.58

heder

0.57

uarts

0.57

%");

0.57

TestBed

0.55

 betweenstory

0.55

Activations Density 0.552%

references to relationships and interactions between entities in various contexts

No Comments

No Known Activations