INDEX

Explanations

references to arms and their positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 disponibilités

-1.00

 Moreau

-0.73

 Kunt

-0.72

alty

-0.72

Еще

-0.71

 pure

-0.71

νώ

-0.70

Rè

-0.69

 GIPHY

-0.68

Mako

-0.68

POSITIVE LOGITS

arm

1.90

 arms

1.90

Arm

1.81

 Arms

1.77

Arm

1.67

arm

1.58

ARM

1.58

Arms

1.57

 ARMS

1.48

 braço

1.47

Activations Density 0.069%

references to arms and their positions

No Comments

No Known Activations