INDEX

Explanations

mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/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.15.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

 itſelf

-0.45

 considérons

-0.42

Conditions

-0.41

ſtance

-0.41

Plugins

-0.40

 algod

-0.40

Steps

-0.40

 uſed

-0.39

drei

-0.39

没事

-0.39

POSITIVE LOGITS

一个个

0.48

UnitTesting

0.46

各个

0.42

 SEDS

0.41

每個

0.41

 Every

0.41

 &___

0.40

 each

0.39

 виправивши

0.39

Каждый

0.39

Activations Density 1.807%

mathematical expressions and symbols

No Comments

No Known Activations