INDEX

Explanations

connections between neurobiological factors and health-related issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 marquées

-0.73

 générations

-0.67

 pouvoirs

-0.67

 gouvernements

-0.65

 scarpe

-0.65

 superiori

-0.64

Semitism

-0.63

 supérieures

-0.62

holdet

-0.62

 peines

-0.61

POSITIVE LOGITS

styleType

0.62

 betweenstory

0.58

SizeF

0.57

hoeddwyd

0.57

featureID

0.57

тических

0.57

Diweddarwch

0.57

󠁣

0.55

 varargin

0.54

 Signalez

0.54

Activations Density 1.024%

connections between neurobiological factors and health-related issues

No Comments

No Known Activations