INDEX

Explanations

programming terminology related to conditions and configurations in software or systems

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

tagHelperRunner

-1.02

parsedMessage

-0.98

TypedDataSet

-0.92

 Taktlose

-0.86

ThroughAttribute

-0.84

contentLoaded

-0.81

 GenerationType

-0.81

 Roskov

-0.80

AsUp

-0.78

 autorytatywna

-0.77

POSITIVE LOGITS

0.35

un

0.28

<eos>

0.28

↵↵

0.28

 closely

0.28

 getrennt

0.28

line

0.27

 align

0.27

Activations Density 0.640%

programming terminology related to conditions and configurations in software or systems

No Comments

No Known Activations