INDEX

Explanations

numerical values and their contextual variation

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

 Económica

-0.58

 Ausdrücke

-0.55

 Empfindung

-0.54

 Züge

-0.51

 łóż

-0.51

jenigen

-0.50

 Psicología

-0.49

 Gegenwart

-0.48

 inalámbrica

-0.48

TokenNameLPAREN

-0.48

POSITIVE LOGITS

Al

0.63

0.58

Al

0.57

0.56

Ro

0.56

Re

0.56

Activations Density 0.001%

numerical values and their contextual variation

No Comments

No Known Activations