INDEX

Explanations

function definitions and calls related to parsing data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 numberWith

-0.86

 onlyOwner

-0.81

 &___

-0.79

defineProperty

-0.74

 StatefulWidget

-0.73

帖最后由

-0.73

systemctl

-0.72

Obrázky

-0.71

Revenir

-0.70

encodeWith

-0.69

POSITIVE LOGITS

 parse

2.36

parse

2.32

 Parse

2.28

Parse

2.16

 parsing

1.82

 Parsing

1.73

PARSE

1.67

 parsed

1.65

Parsing

1.60

Parser

1.52

Activations Density 0.045%

function definitions and calls related to parsing data

No Comments

No Known Activations