INDEX

Explanations

concepts related to purity and cleanliness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 devenus

-0.75

 envers

-0.66

 coscienza

-0.65

 aveug

-0.64

NOPQRST

-0.62

 fallu

-0.61

 lentement

-0.61

 ovunque

-0.61

 manquante

-0.60

 lettera

-0.60

POSITIVE LOGITS

 pure

1.11

Pure

1.04

 Pure

1.03

pure

1.00

 purely

0.92

 PURE

0.84

PURE

0.81

RectangleBorder

0.79

 puro

0.75

 pura

0.74

Activations Density 0.106%

concepts related to purity and cleanliness

No Comments

No Known Activations