INDEX

Explanations

references to equations and figures in a mathematical or scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

amo

-0.60

giri

-0.56

Chi

-0.56

 findBy

-0.56

es

-0.55

Att

-0.55

aaaaaaaa

-0.55

magin

-0.54

POSITIVE LOGITS

 Monfieur

0.72

 myſelf

0.70

 înc

0.69

 Dumnezeu

0.68

 negru

0.68

 ainfi

0.68

 deschis

0.68

 laſt

0.67

 themſelves

0.66

 bağlantılar

0.66

Activations Density 0.879%

references to equations and figures in a mathematical or scientific context

No Comments

No Known Activations