INDEX

Explanations

technical terminology related to health and biological processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.50

-0.49

-0.44

-0.43

↵

-0.43

PC

-0.42

will

-0.42

for

-0.42

</strong>

-0.42

POSITIVE LOGITS

ValueStyle

1.26

 Monfieur

1.09

 neceff

1.02

ReusableCell

1.02

 ſtate

1.00

 houſe

1.00

 itſelf

0.98

 purpoſe

0.96

Efq

0.96

styleType

0.95

Activations Density 1.724%

technical terminology related to health and biological processes

No Comments

No Known Activations