INDEX

Explanations

statements and discussions expressed by individuals, often focusing on opinions, positions, or actions taken in specific contexts

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

OGND

-0.46

 ***!

-0.39

ItemLayout

-0.37

İstinadlar

-0.36

الحياه

-0.36

namespace

-0.35

favor

-0.35

 Instrum

-0.35

entier

-0.34

sieger

-0.34

POSITIVE LOGITS

 himself

1.15

himself

1.02

 herself

0.75

 himſelf

0.71

 Himself

0.65

herself

0.63

+#+

0.60

 powinien

0.60

 चाहता

0.59

 kanyang

0.58

Activations Density 0.739%

statements and discussions expressed by individuals, often focusing on opinions, positions, or actions taken in specific contexts

No Comments

No Known Activations