INDEX

Explanations

elements related to programming and technical syntax

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

numbers with ±

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

mbggenerated

-0.37

extendable

-0.34

urized

-0.34

urable

-0.33

 consigo

-0.32

륭

-0.31

못

-0.31

 venía

-0.31

 distanciation

-0.31

PointerException

-0.30

POSITIVE LOGITS

 يتيمه

0.77

 disambiguazione

0.68

bootstrapcdn

0.60



0.52

évaluateur

0.51

 ویکی‌پدی

0.48

+#+#

0.48

 VIDEOTAPE

0.47

لينكات

0.47

Gigi

0.47

Activations Density 0.060%

elements related to programming and technical syntax

numbers with ±

No Comments

No Known Activations