INDEX

Explanations

information related to memory limits and data capacities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

RegressionTest

-0.83

出版年

-0.80

ViewFeatures

-0.75

 autorytatywna

-0.73

:✨

-0.73

SequentialGroup

-0.70

jsxFileName

-0.70

تقاوى

-0.70

moveToFirst

-0.66

 مشين

-0.65

POSITIVE LOGITS

max

0.96

 limit

0.95

 maximum

0.89

 Maximum

0.81

Maximum

0.79

 Limit

0.78

max

0.76

Max

0.76

 maksimum

0.75

Limit

0.74

Activations Density 0.338%

information related to memory limits and data capacities

No Comments

No Known Activations