INDEX

Explanations

words related to versatility and multiple uses of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ValueStyle

-0.65

 propOrder

-0.64

RenderAtEndOf

-0.64

oredCriteria

-0.58

 cérami

-0.52

LookAnd

-0.51

verwijspagina

-0.51

nodoc

-0.50

 producteurs

-0.50

 Bessel

-0.49

POSITIVE LOGITS

期刊论文

0.58

findpost

0.54

ifoli

0.53

tku

0.53

 Rugg

0.52

use

0.52

Демографія

0.52

 place

0.51

 suitability

0.50

applicable

0.50

Activations Density 0.180%

words related to versatility and multiple uses of items

No Comments

No Known Activations