INDEX

Explanations

words and phrases related to re-evaluation or re-assessment processes

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

after "re-" prefix

np_acts-logits-general · gemini-2.0-flash

re- prefix followed by action

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

 excru

-0.62

providedIn

-0.58

 HttpNotFound

-0.57

ViewChild

-0.53

 préfé

-0.52

xaml

-0.51

Datuak

-0.51

 تانيه

-0.51

produzione

-0.51

fört

-0.49

POSITIVE LOGITS

tool

0.54

 Struct

0.53

orient

0.52

 struct

0.51

jig

0.50

engineering

0.50

energ

0.49

Schedulers

0.49

ener

0.48

struct

0.48

Activations Density 0.200%

words and phrases related to re-evaluation or re-assessment processes

after "re-" prefix

re- prefix followed by action

No Comments

No Known Activations