INDEX

Explanations

programming-related keywords and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

MLLoader

-0.76

rungsseite

-0.71

SourceChecksum

-0.68

 مشين

-0.65

 disambiguazione

-0.63

 ExecuteAsync

-0.63

 الحره

-0.62

舺

-0.61

 GenerationType

-0.59

 चीज़ों

-0.58

POSITIVE LOGITS

sot

0.36

Pyx

0.36

 препратки

0.34

edding

0.33

Mar

0.33

ricing

0.33

inder

0.32

<eos>

0.32

COND

0.32

 перевод

0.32

Activations Density 1.991%

programming-related keywords and structures

No Comments

No Known Activations