INDEX

Explanations

terms that indicate relationships or connections to specific features or protocols

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

ginx

-0.68

 alpina

-0.67

 tecn

-0.64

 vaut

-0.63

 Wylie

-0.63

 IActionResult

-0.63

 latine

-0.62

tek

-0.62

gulier

-0.61

ソリン

-0.61

POSITIVE LOGITS

 associations

1.26

 associates

1.25

 assoc

1.17

 association

1.16

 associ

1.14

 Associations

1.09

associ

1.08

 associating

1.08

associations

1.06

 associate

1.06

Activations Density 0.079%

terms that indicate relationships or connections to specific features or protocols

No Comments

No Known Activations