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-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 alimentaria

-0.40

 userSchema

-0.36

 laquelle

-0.35

 perlas

-0.34

lač

-0.34

 annuelle

-0.34

 rayas

-0.34

 αυτή

-0.32

 enseignants

-0.31

 lesquelles

-0.31

POSITIVE LOGITS

ConstraintMaker

0.70

StoryboardSegue

0.64

adaptiveStyles

0.63

Aholisi

0.57

ActionCreators

0.57

 незавершена

0.56

 виправивши

0.56

 dAtA

0.51

tonsoft

0.51

 XCTest

0.51

Activations Density 0.009%

mathematical symbols and notation used in equations

No Comments

No Known Activations