INDEX

Explanations

function definitions and documentation comments in programming code

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.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

 RemoteException

-0.76

 abbandon

-0.62

EDEFAULT

-0.59

 EClass

-0.59

+#+

-0.59

SerializedSize

-0.58

 sonno

-0.58

LLVM

-0.58

Cyfarwyddwr

-0.57

 priesthood

-0.56

POSITIVE LOGITS

AnchorStyles

0.71

 kasarigan

0.69

Hauptartikel

0.59

]")]

0.57

 بيها

0.56

béco

0.55

SequentialGroup

0.54

 MainAxisSize

0.52

FTFY

0.52

ReusableCell

0.51

Activations Density 0.043%

function definitions and documentation comments in programming code

No Comments

No Known Activations