INDEX

Explanations

statements or references related to community engagement and individual experiences

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

Followed by verbs related to thoughts or actions

np_acts-logits-general · gemini-2.0-flash

Pronouns followed by desire or decision verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

RegressionTest

-0.79

InputBorder

-0.74

horabuena

-0.63

 وتسجيلات

-0.63

 doInBackground

-0.63

TagHelper

-0.62

Gweler

-0.60

 Roskov

-0.58

XtraEditors

-0.58

uspiel

-0.58

POSITIVE LOGITS

 decided

1.98

 wanted

1.74

decided

1.50

 Decided

1.49

wanted

1.33

Decided

1.30

 decidió

1.23

 decides

1.21

 felt

1.19

 deciso

1.18

Activations Density 0.318%

statements or references related to community engagement and individual experiences

Followed by verbs related to thoughts or actions

Pronouns followed by desire or decision verbs

No Comments

No Known Activations