INDEX

Explanations

terms related to feeding or nutrition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 increí

-0.75

 parachoque

-0.74

 ſind

-0.70

aimeJ

-0.70

 Infór

-0.68

ientras

-0.68

majánló

-0.68

imachinery

-0.67

pecabe

-0.66

 ivelany

-0.66

POSITIVE LOGITS

 feed

1.01

fed

1.00

 feeding

0.88

feed

0.85

 feeds

0.85

 Feder

0.77

 federal

0.76

Feed

0.76

 Federation

0.76

 Federal

0.75

Activations Density 0.175%

terms related to feeding or nutrition

No Comments

No Known Activations