INDEX

Explanations

terms related to telecommunications services and medical research

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

concept and associated outcome

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 informée

-0.64

 beginnetje

-0.60

richTextPanel

-0.58

تقاوى

-0.56

 <<<<<<<<<<<<<<

-0.54

Autoritní

-0.52

mergeFrom

-0.48

 demais

-0.48

Diweddarwch

-0.47

 autorytatywna

-0.46

POSITIVE LOGITS

modelBuilder

0.46

 ſind

0.42

일에

0.41

Ϣ

0.40

IntoConstraints

0.40

]$}

0.39

AABB

0.39

iempo

0.39

ſelves

0.38

—

0.38

Activations Density 0.207%

terms related to telecommunications services and medical research

concept and associated outcome

No Comments

No Known Activations