INDEX

Explanations

references and comparisons to other entities or concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emb

-0.57

 many

-0.56

 Brind

-0.56

 kaarangay

-0.55

 some

-0.54

MANY

-0.50

kot

-0.50

 saker

-0.50

idak

-0.49

iastes

-0.49

POSITIVE LOGITS

 AssemblyCompany

0.71

AlterField

0.67

ddots

0.63

EDEFAULT

0.62

reactstrap

0.62

)_/¯

0.62

ngdoc

0.61

nocześnie

0.61

PerformLayout

0.60

WriteTagHelper

0.60

Activations Density 0.107%

references and comparisons to other entities or concepts

No Comments

No Known Activations