INDEX

Explanations

specific scientific terms and parameters related to research and analysis

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

 Majefty

-0.77

 pleaſure

-0.75

 fubject

-0.56

 difp

-0.55

Tembelea

-0.52

SocketChannel

-0.52

 deſt

-0.51

chalet

-0.51

RECOMMEND

-0.51

 étag

-0.50

POSITIVE LOGITS

1.18

es

0.98

bs

0.91

ens

0.88

nes

0.84

zs

0.83

os

0.82

ks

0.82

ses

0.82

ras

0.79

Activations Density 1.599%

specific scientific terms and parameters related to research and analysis

No Comments

No Known Activations