INDEX

Explanations

terms related to validation and data integrity

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Chham

-0.75

ೊ

-0.72

 Esquire

-0.72

OIR

-0.69

 Ocho

-0.69

ese

-0.69

Os

-0.68

Obe

-0.67

acağı

-0.67

zee

-0.67

POSITIVE LOGITS

Val

1.26

VAL

1.23

val

1.11

 Valdez

1.10

 vali

1.10

 Valky

1.07

Val

1.05

VAL

1.03

]")]

1.00

 VALENT

0.96

Activations Density 0.078%

terms related to validation and data integrity

No Comments

No Known Activations