INDEX

Explanations

elements and syntax used in programming or markup languages

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

AccessorTable

-0.65

RegressionTest

-0.62

 שוליים

-0.60

InputTagHelper

-0.56

IntoConstraints

-0.55

OrWhiteSpace

-0.53

postsleuth

-0.53

oolean

-0.52

SequentialGroup

-0.52

saraba

-0.52

POSITIVE LOGITS

 again

0.38

 mismas

0.37

Again

0.34

 EconPapers

0.33

 nuevamente

0.33

again

0.32

 ск

0.32

 tekrar

0.32

 yine

0.32

 större

0.30

Activations Density 0.006%

elements and syntax used in programming or markup languages

No Comments

No Known Activations