INDEX

Explanations

technical terminology and concepts related to typesetting and printing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-0.82

 Theſe

-0.72

 prêts

-0.66

 ſeveral

-0.64

 ſmall

-0.63

 Monfieur

-0.63

 purpoſe

-0.63

những

-0.62

 himſelf

-0.61

 greateſt

-0.61

POSITIVE LOGITS

 kasarigan

0.81

 Référence

0.70

RegressionTest

0.67

<?

0.63

 ***!

0.62

 referrerpolicy

0.59

يديا

0.59

 Walkover

0.57

MigrationBuilder

0.56

 defaultstate

0.56

Activations Density 1.204%

technical terminology and concepts related to typesetting and printing processes

No Comments

No Known Activations