INDEX

Explanations

occurrences of the word "Los."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

 CreateTagHelper

-0.56

SharedDtor

-0.53

resizingMask

-0.48

interopRequire

-0.47

Jîn

-0.46

はじめに

-0.45

pantalón

-0.45

QMetaType

-0.44

 mikina

-0.44

 pantallas

-0.43

POSITIVE LOGITS

 Angeles

0.49

 Angles

0.45

 angles

0.44

Cab

0.43

inj

0.43

Ala

0.42

artan

0.40

siem

0.40

Os

0.39

 Lonely

0.37

Activations Density 0.201%

occurrences of the word "Los."

No Comments

No Known Activations