INDEX

Explanations

words related to cooking or cookbooks

oai_token-act-pair · gemini-2.0-flash

cooking

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

balleur

-0.60

StructEnd

-0.60

 Baillargeon

-0.59

setVerticalGroup

-0.58

UserScript

-0.56

 AssemblyCompany

-0.56

EndContext

-0.56

postsleuth

-0.55

ToProps

-0.54

::_('

-0.52

POSITIVE LOGITS

 DECK

0.56

PyErr

0.53

 avancé

0.49

Externí

0.48

 StatefulWidget

0.47

jardin

0.46

 NSCoder

0.46

 réglable

0.45

 Bibliote

0.45

 manuelle

0.45

Activations Density 0.679%

words related to cooking or cookbooks

cooking

No Comments

No Known Activations