INDEX

Explanations

recommendations for best practices in various contexts, particularly related to coding and functionality

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

EndInit

-0.56

PerformLayout

-0.53

NewGuid

-0.48

JsonPropertyName

-0.48

BeginInit

-0.43

mortal

-0.43

 Stuhl

-0.43

 suddenly

-0.42

 Constitu

-0.42

SaveChanges

-0.42

POSITIVE LOGITS

 prefer

0.81

 Prefer

0.74

Prefer

0.73

 prefers

0.73

prefer

0.72

 sebaiknya

0.68

 preferable

0.61

 preferably

0.61

preferred

0.61

 liever

0.60

Activations Density 0.412%

recommendations for best practices in various contexts, particularly related to coding and functionality

No Comments

No Known Activations