INDEX

Explanations

function definitions and initializations in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

říklad

-0.63

OBB

-0.55

BeginContext

-0.55

amarin

-0.54

imwrite

-0.54

 wiederholt

-0.54

 meanwhile

-0.53

 kenyataan

-0.53

 Bany

-0.53

InputBorder

-0.53

POSITIVE LOGITS

this

0.81

initComponents

0.68

 this

0.64

Initialize

0.59

BeginInit

0.56

sizeCache

0.56

init

0.55

).__

0.54

ButterKnife

0.52

ArgsConstructor

0.51

Activations Density 0.047%

function definitions and initializations in programming code

No Comments

No Known Activations