INDEX

Explanations

references to lists and their elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

midler

-0.58

ViewType

-0.53

SpringRunner

-0.51

orini

-0.51

utives

-0.51

 DBNull

-0.51

ilirsiniz

-0.51

érrez

-0.50

oxia

-0.50

ventes

-0.49

POSITIVE LOGITS

 list

1.69

 lists

1.52

 listing

1.36

 liste

1.31

 Lists

1.29

 lijst

1.29

 Liste

1.27

 List

1.25

 lista

1.24

 LIST

1.22

Activations Density 0.191%

references to lists and their elements

No Comments

No Known Activations