INDEX

Explanations

mathematical constructs and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

licet

-0.63

sheets

-0.63

mew

-0.62

 विश्वसनीयता

-0.60

eaky

-0.59

imea

-0.58

csolódó

-0.57

存于互联网档案馆

-0.56

TagHelper

-0.56

ArgsConstructor

-0.56

POSITIVE LOGITS

ValueStyle

0.69

Personendaten

0.68

SuccessListener

0.66

AutoScale

0.66

UserScript

0.65

UnsafeEnabled

0.64

complexContent

0.63

CompleteListener

0.61

webElementXpaths

0.60

 doInBackground

0.60

Activations Density 1.106%

mathematical constructs and expressions

No Comments

No Known Activations