INDEX

Explanations

structures or elements within JSON-like data

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

Tikang

-0.63

ocry

-0.55

ởi

-0.54

VertexAttrib

-0.53

timewa

-0.52

sendStatus

-0.52

 pasto

-0.52

ô

-0.52

avigation

-0.52

}/${

-0.52

POSITIVE LOGITS

 InputDecoration

0.77

 שוליים

0.73

JoinTable

0.62

তথ্যসূত্র

0.60

ViewImports

0.58

":[{

0.58

 يتيمه

0.57

liferay

0.57

談社

0.57

ագրություններ

0.57

Activations Density 0.207%

structures or elements within JSON-like data

No Comments

No Known Activations