INDEX

Explanations

numerical and evaluative results related to data or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Majefty

-1.14

 raiſ

-1.09

 itſelf

-1.07

ſelf

-1.07

 Monfieur

-1.07

Efq

-1.07

 ſtate

-1.06

 Houſe

-1.05

 myſelf

-1.04

 Reſ

-1.04

POSITIVE LOGITS

 every

0.56

WindowConstants

0.51

0.50

0.49

no

0.48

 rueda

0.48

not

0.48

blica

0.48

odal

0.48

thral

0.47

Activations Density 0.325%

numerical and evaluative results related to data or processes

No Comments

No Known Activations