INDEX

Explanations

function definitions within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

EntityFramework

-0.53

ViewFeatures

-0.48

op

-0.47

 EventArgs

-0.46

venant

-0.43

arden

-0.43

 ancaman

-0.43

IndexOf

-0.41

CharField

-0.40

sel

-0.40

POSITIVE LOGITS

 onCreate

1.50

onCreate

1.38

InputTagHelper

1.33

VersionUID

1.26

 cref

1.18

+:+

1.13

HasColumnType

1.02

+#+

0.97

 незавершена

0.93

 CreateTagHelper

0.91

Activations Density 0.004%

function definitions within code

No Comments

No Known Activations