INDEX

Explanations

numerical data 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 @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 AssemblyCulture

-0.51

⤹

-0.39

chaub

-0.38

合

-0.34

 cata

-0.34

pas

-0.32

httphttps

-0.32

skj

-0.32

izing

-0.32

像

-0.32

POSITIVE LOGITS

RegressionTest

0.59

]=>

0.59

 pinulongan

0.51

tanleria

0.45

 ninety

0.45

FunctionFlags

0.45

 Ninety

0.43

Autoritní

0.43

LabelTagHelper

0.43

LAUGHTER

0.42

Activations Density 1.049%

numerical data and symbols

No Comments

No Known Activations

numerical data and symbols

No Comments

No Known Activations