INDEX

Explanations

medical terms and classifications related to tumors

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-1.03

 Administrativna

-0.93

 estekak

-0.88

 '\\;'

-0.85

fjspx

-0.80

+#+

-0.76

 صوتيه

-0.74

__":

-0.73

المكان

-0.73

 resourceCulture

-0.72

POSITIVE LOGITS

렇

0.59

Lid

0.52

timedelta

0.47

POINTER

0.47

Sci

0.45

Nw

0.44

ForKey

0.44

doi

0.44

SneakyThrows

0.44

brainly

0.43

Activations Density 0.007%

medical terms and classifications related to tumors

No Comments

No Known Activations