INDEX

Explanations

expressions of personal opinions and judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 reportedly

-0.61

vat

-0.54

 supposedly

-0.54

 supuestamente

-0.52

<bos>

-0.51

 известно

-0.48

 apparently

-0.48

on

-0.47

POSITIVE LOGITS

 فريبيس

1.36

 للمعارف

1.06

 NSCoder

1.06

 تانيه

1.04

Демографія

1.00

WebElementEntity

1.00

featureID

0.97

MessageTagHelper

0.94

EndInit

0.90

adaptiveStyles

0.89

Activations Density 0.325%

expressions of personal opinions and judgments

No Comments

No Known Activations