INDEX

Explanations

references to specific locations and people related to events or concepts

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

Memphis

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

出版年

-0.44

twimg

-0.39

IonicModule

-0.39

 sura

-0.37

 चीज़ों

-0.36

 output

-0.36

 ronde

-0.35

PagerAdapter

-0.34

ter

-0.34

BoxShadow

-0.34

POSITIVE LOGITS

 Memphis

1.05

Memphis

1.00

memp

0.72

 Grizzlies

0.72

 memp

0.71

zzlies

0.66

 Colli

0.65

 FedEx

0.58

 Beale

0.58

 Shelby

0.56

Activations Density 0.026%

references to specific locations and people related to events or concepts

Memphis

No Comments

No Known Activations