INDEX

Explanations

function and method definitions in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InitVars

-0.72

 Roskov

-0.63

aarrggbb

-0.61

↵↵

-0.60

Spoljašnje

-0.60

 OFDb

-0.55

parsedMessage

-0.53

MessageOf

-0.51

 pory

-0.50

 Wicidata

-0.50

POSITIVE LOGITS

 }}$}

0.87

ſelves

0.74

 InputDecoration

0.74

 ſind

0.71

bibfield

0.66

ſelf

0.66

</caption>

0.65

″]

0.64

 StatelessWidget

0.64

 NSCoder

0.62

Activations Density 0.013%

function and method definitions in code snippets

No Comments

No Known Activations