INDEX

Explanations

elements of technical documentation or coding error messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 للمعارف

-0.74

 noDo

-0.73

 PeEnEo

-0.72

IVEREF

-0.67

 beginnetje

-0.67

Derbyniad

-0.65

(!__

-0.65

 getApp

-0.63

 Chwiliwch

-0.63

Tembelea

-0.63

POSITIVE LOGITS

しかし

0.48

tualmente

0.46

 actualidad

0.45

ちなみに

0.45

 actually

0.44

この

0.43

ただ

0.43

 noiva

0.43

 although

0.43

当然

0.41

Activations Density 0.013%

elements of technical documentation or coding error messages

No Comments

No Known Activations