INDEX

Explanations

descriptions of size, weight, and cost related to products or materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

 adjustment

-0.40

 straightforward

-0.40

 simple

-0.34

 provided

-0.34

StringUtil

-0.33

adjustment

-0.33

adjust

-0.33

 transformative

-0.32

 dimension

-0.32

 informal

-0.32

POSITIVE LOGITS

aarrggbb

0.68

 terlalu

0.67

 ब्रेकडाउन

0.66

Worse

0.66

ſelves

0.65

 AssemblyCompany

0.64

Билгалдахарш

0.64

 unnecessarily

0.63

 kasarigan

0.63

 CreateTagHelper

0.63

Activations Density 0.903%

descriptions of size, weight, and cost related to products or materials

No Comments

No Known Activations