INDEX

Explanations

expressions of positive feelings and recommendations regarding experiences or products

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

First person perspective, beginnings of sentences

np_acts-logits-general · gemini-2.0-flash

I/we statements

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

PYX

-0.65

usehen

-0.51

 Dernière

-0.49

UserScript

-0.49

setVerticalGroup

-0.48

DIPSETTING

-0.48

styleType

-0.48

efully

-0.47

ంత

-0.47

pire

-0.47

POSITIVE LOGITS

 GenerationType

0.61

AddHtmlAttribute

0.58

rungsseite

0.56

 RECOMMEND

0.54

 FetchType

0.52

makeConstraints

0.52

 Recommend

0.52

 recommande

0.51

KeySpec

0.51

 recommend

0.50

Activations Density 0.097%

expressions of positive feelings and recommendations regarding experiences or products

First person perspective, beginnings of sentences

I/we statements

No Comments

No Known Activations