INDEX

Explanations

mentions of specific names, acronyms, or entities, particularly those related to computing and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ISupport

-0.70

KommentareTeilen

-0.58

ofern

-0.58

ValueStyle

-0.58

 complementa

-0.58

ting

-0.58

 Waray

-0.57

HomeAsUpEnabled

-0.56

RenderAtEndOf

-0.54

lines

-0.54

POSITIVE LOGITS

uuuu

0.89

uuu

0.84

uuuuu

0.76

du

0.72

uu

0.70

udu

0.65

 Brute

0.62

"@/

0.61

UUUU

0.60

Activations Density 0.324%

mentions of specific names, acronyms, or entities, particularly those related to computing and programming

No Comments

No Known Activations