INDEX

Explanations

occurrences of a specific variable or function within mathematical contexts

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

MarshalTo

-0.66

دانشنامهٔ

-0.66

uxxxx

-0.63

 Nicho

-0.62

Jeografia

-0.60

ceğine

-0.60

onai

-0.60

Personendaten

-0.60

 Carro

-0.59

expandindo

-0.59

POSITIVE LOGITS

1.02

0.99

getF

0.91

0.87

 getF

0.84

ｆ

0.73

xf

0.70

फ

0.66

Ф

0.66

Activations Density 0.139%

occurrences of a specific variable or function within mathematical contexts

No Comments

No Known Activations