INDEX

Explanations

references to statistics and rankings related to institutions or groups

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

ValueStyle

-0.63

lorette

-0.56

atra

-0.50

 alter

-0.48

 שוליים

-0.46

 allé

-0.44

 maturation

-0.44

webElementGuid

-0.43

itemView

-0.43

意思

-0.43

POSITIVE LOGITS

 safest

0.65

 loudest

0.61

Least

0.60

Coordonnées

0.59

 cleanest

0.59

asiest

0.56

 가장

0.55

DockStyle

0.55

 surla

0.55

 richest

0.55

Activations Density 0.294%

references to statistics and rankings related to institutions or groups

No Comments

No Known Activations