INDEX

Explanations

terms related to reported observations, categories, or classifications in scientific studies

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

੝

-0.62

SharedDtor

-0.60

TagMode

-0.54

cruise

-0.54

BeginInit

-0.51

 للمعارف

-0.51

ſelben

-0.50

litude

-0.49

ThroughAttribute

-0.49

 zuſammen

-0.49

POSITIVE LOGITS

 Sprachen

0.40

ài

0.38

 leçon

0.35

 empre

0.34

 Италијани

0.34

หาร

0.33

 Gubernur

0.32

分

0.31

ペア

0.31

 Ekonomi

0.30

Activations Density 0.956%

terms related to reported observations, categories, or classifications in scientific studies

No Comments

No Known Activations