INDEX

Explanations

phrases related to limits, restrictions, and managing capacities or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.79

abestanden

-0.69

:+:

-0.67

httphttps

-0.66

#+#

-0.64

DockStyle

-0.64

+#+#

-0.62

 snippetHide

-0.62

出版年

-0.61

 للاسماء

-0.61

POSITIVE LOGITS

 limit

1.19

 Limit

0.97

Limit

0.93

limit

0.92

 limits

0.90

max

0.88

 maximum

0.85

 limite

0.84

 límite

0.83

 limitar

0.81

Activations Density 0.376%

phrases related to limits, restrictions, and managing capacities or resources

No Comments

No Known Activations

phrases related to limits, restrictions, and managing capacities or resources

No Comments

No Known Activations