INDEX

Explanations

terms associated with estimations or approximations in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

alnız

-0.67

 وتسجيلات

-0.62

WriteTagHelper

-0.61

 Wirklichkeit

-0.60

出版年

-0.59

ที

-0.55

 Illy

-0.54

 Renewal

-0.53

 Madera

-0.53

('');

-0.52

POSITIVE LOGITS

approx

1.53

 approx

1.51

 Approx

1.46

Approx

1.35

 approximately

1.26

 Approximately

1.24

Approximately

1.22

approximately

1.21

 aprox

1.12

 roughly

1.09

Activations Density 0.128%

terms associated with estimations or approximations in data

No Comments

No Known Activations