INDEX

Explanations

words related to the capability or potential of various concepts or entities

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

words ending in "able" that describe capabilities or conditions.

oai_token-act-pair · gpt-4o Triggered by @timna

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 سكانية

-0.62

RegressionTest

-0.59

 Waray

-0.58

setupUi

-0.56

jspx

-0.56

 negativ

-0.52

 AspNetCore

-0.50

wts

-0.50

UserScript

-0.50

📫

-0.49

POSITIVE LOGITS

vable

0.80

illable

0.80

rowable

0.79

codable

0.78

mable

0.76

 attainable

0.76

able

0.76

pable

0.76

izable

0.75

atable

0.75

Activations Density 0.526%

words related to the capability or potential of various concepts or entities

words ending in "able" that describe capabilities or conditions.

No Comments

No Known Activations