INDEX

Explanations

statements that evaluate the quality or impact of various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

uxxxx

-0.73

 ModelExpression

-0.69

 Vikipedi

-0.63

Those

-0.61

OGND

-0.60

Hentet

-0.59

 Those

-0.58

Referanser

-0.58

+:+

-0.57

those

-0.56

POSITIVE LOGITS

 acestei

0.61

 zamanda

0.59

 laikā

0.59

WebServlet

0.56

farande

0.54

 للمعارف

0.54

 durian

0.53

 provar

0.53

бята

0.52

 prova

0.52

Activations Density 0.314%

statements that evaluate the quality or impact of various topics

No Comments

No Known Activations