INDEX

Explanations

mathematical symbols and notation used in equations

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

 للمعارف

-0.77

 autorytatywna

-0.74

 verſch

-0.73

 beſte

-0.72

évaluateur

-0.72

OCCURRED

-0.70

 betweenstory

-0.69

 Geſch

-0.69

 MainAxisSize

-0.68

 myſelf

-0.68

POSITIVE LOGITS

 Thus

0.29

 Then

0.29

PreExecute

0.27

__':

0.27

__":

0.26

Another

0.26

 carteira

0.25

${

0.25

 Another

0.25

Activations Density 0.391%

mathematical symbols and notation used in equations

No Comments

No Known Activations