INDEX

Explanations

numerical data and statistics related to medical research

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

numbers and measurements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 '\\;'

-0.80

ագրություններ

-0.68

Vidite

-0.64

 nakalista

-0.59

+#+#

-0.59

Bakgrunnsstoff

-0.59

Tembelea

-0.57

 Roskov

-0.57

 pinulongan

-0.54

 snippetHide

-0.54

POSITIVE LOGITS

sample

0.39

Sample

0.36

dis

0.35

 jenner

0.35

 Dafür

0.35

 Flach

0.35

Middle

0.34

 Inſ

0.34

middle

0.34

 sample

0.34

Activations Density 0.091%

numerical data and statistics related to medical research

numbers and measurements

No Comments

No Known Activations