INDEX

Explanations

specific dates and numeric values related to events or statistics

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

as of a date

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

SequentialGroup

-0.54

 Anschließend

-0.54

라는

-0.49

Predecesor

-0.48

as

-0.47

 dès

-0.46

 للمعارف

-0.44

 sebagai

-0.44

最初は

-0.42

extAlignment

-0.42

POSITIVE LOGITS

为止

0.71

 Wicidata

0.57

 statistics

0.53

 cumulative

0.50

 hadn

0.48

TRAILING

0.47

 belum

0.47

 estimates

0.47

统计

0.47

 none

0.46

Activations Density 0.024%

specific dates and numeric values related to events or statistics

as of a date

No Comments

No Known Activations