INDEX

Explanations

terms and phrases related to biological or medical data and experimental procedures

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

Tokens after capitalized words

np_acts-logits-general · gemini-2.0-flash

names and letters associated with entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AnchorStyles

-0.71

 ब्रेकडाउन

-0.68

RegressionTest

-0.64

TargetException

-0.61

 Infórmanos

-0.61

toppers

-0.60

<unused51>

-0.60

<unused74>

-0.60

<unused42>

-0.60

<unused16>

-0.60

POSITIVE LOGITS

 above

0.28

Above

0.27

 Utility

0.27

above

0.26

farwyddwr

0.24

Ouv

0.23

 Util

0.23

vician

0.23

 précédemment

0.23

 Above

0.23

Activations Density 0.710%

terms and phrases related to biological or medical data and experimental procedures

Tokens after capitalized words

names and letters associated with entities

No Comments

No Known Activations