INDEX

Explanations

terms related to peer review processes

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

Questions asking for permission or preference

np_acts-logits-general · gemini-2.0-flash

as required

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.65

in

-0.63

for

-0.60

and

-0.58

 just

-0.57

by

-0.57

to

-0.55

the

-0.55

on

-0.54

POSITIVE LOGITS

ViewFeatures

1.38

 незавершена

1.35

Personensuche

1.33

TypedDataSet

1.32

 дописавши

1.31

IntoConstraints

1.31

 CreateTagHelper

1.27

 ModelExpression

1.25

expandindo

1.24

ScopeManager

1.24

Activations Density 0.194%

terms related to peer review processes

Questions asking for permission or preference

as required

No Comments

No Known Activations