INDEX

Explanations

references to technology and computational concepts related to efficiency and structure

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

technical terms and entities

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

 مفص

-0.41

lugin

-0.39

 relieving

-0.38

 Lauf

-0.38

 Erscheinung

-0.37

 fakt

-0.37

허

-0.37

 diffé

-0.36

hares

-0.36

getAdapter

-0.36

POSITIVE LOGITS

#+#

0.61

EDEFAULT

0.56

enderror

0.56

unless

0.53

 AssemblyCulture

0.51

setVerticalGroup

0.50

 unless

0.49

GEBURTSDATUM

0.47

StoryboardSegue

0.47

 anymore

0.46

Activations Density 0.075%

references to technology and computational concepts related to efficiency and structure

technical terms and entities

No Comments

No Known Activations