INDEX

Explanations

technical vocabulary related to programming, particularly involving function definitions and conditional requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/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.36.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

parsedMessage

-0.56

السكان

-0.44

!*\

-0.42

 télévis

-0.41

 AssemblyVersion

-0.40

DotNetBar

-0.40

localctx

-0.40

 pohled

-0.39

 poświę

-0.39

 informée

-0.38

POSITIVE LOGITS

 works

2.41

 working

2.36

 worked

2.33

working

2.08

 WORKS

2.05

Working

2.03

 WORKING

2.03

 Worked

2.02

 Works

2.00

Worked

1.98

Activations Density 0.989%

technical vocabulary related to programming, particularly involving function definitions and conditional requests

No Comments

No Known Activations