INDEX

Explanations

terms related to medical conditions and their complexities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

]++;

-0.51

rio

-0.47

 astore

-0.47

Skal

-0.46

 թվական

-0.45

Pranala

-0.45

leşti

-0.44

+#+#

-0.44

]=>

-0.43

verti

-0.42

POSITIVE LOGITS

via

1.19

 relying

1.16

 based

1.15

 using

1.12

 through

1.03

 baseado

1.00

 grâce

1.00

via

1.00

靠

0.99

 rely

0.98

Activations Density 1.400%

terms related to medical conditions and their complexities

No Comments

No Known Activations