INDEX

Explanations

references to studies and research findings

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

Followed by "study" or "paper"

np_acts-logits-general · gemini-2.0-flash

in this study

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

+#+#

-0.64

 bocca

-0.58

 Wint

-0.58

ReusableCell

-0.56

deman

-0.53

 lunghi

-0.50

NameInMap

-0.47

chwitz

-0.47

ungkinan

-0.47

biskan

-0.47

POSITIVE LOGITS

 study

2.04

study

1.73

 Study

1.42

Study

1.39

 STUDY

1.36

 paper

1.35

 studies

1.31

STUDY

1.25

 estudo

1.22

 étude

1.20

Activations Density 1.087%

references to studies and research findings

Followed by "study" or "paper"

in this study

No Comments

No Known Activations