INDEX

Explanations

terms related to healthcare and medical research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 utafitiHapana

-0.93

majánló

-0.93

expandindo

-0.87

<unused8>

-0.85

Personendaten

-0.85

<unused42>

-0.85

ftagPool

-0.85

<unused79>

-0.85

<unused16>

-0.85

<unused41>

-0.85

POSITIVE LOGITS

0.37

 accounts

0.32

 because

0.31

0.30

 account

0.29

 ngoại

0.28

 rest

0.28

↵

0.27

 activity

0.27

↵↵

0.26

Activations Density 1.247%

terms related to healthcare and medical research

No Comments

No Known Activations