INDEX

Explanations

data structure elements related to catalog items, including their specifications and attributes

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

Variable/parameter names

np_acts-logits-general · gemini-2.0-flash

code identifiers

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.75

 betweenstory

-0.69

complexContent

-0.69

gyz

-0.64

IUrlHelper

-0.64

Tembelea

-0.62

تقاوى

-0.61

LookAnd

-0.60

اریخ

-0.60

 تانيه

-0.58

POSITIVE LOGITS

RenderAtEndOf

0.71

IonicModule

0.53

ButterKnife

0.53

 consig

0.50

}{*}{}

0.50

DoubleQuotes

0.49

_${

0.49

 استنادى

0.48

umbar

0.48

FTFY

0.48

Activations Density 0.559%

data structure elements related to catalog items, including their specifications and attributes

Variable/parameter names

code identifiers

No Comments

No Known Activations