INDEX

Explanations

structured information related to data entries and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 resourceCulture

-0.63

LookAnd

-0.61

AddTagHelper

-0.59

belajaran

-0.49

NewRow

-0.46

věd

-0.44

deelte

-0.43

 شدن

-0.43

 reutiliz

-0.43

 ngờ

-0.41

POSITIVE LOGITS

 details

0.79

details

0.71

 description

0.68

 '\\;'

0.65

 detail

0.63

 détails

0.63

 detalhes

0.63

nationality

0.62

 detalles

0.60

 particulars

0.60

Activations Density 0.605%

structured information related to data entries and documentation

No Comments

No Known Activations