INDEX

Explanations

mathematical or logical symbols and their placements within a context

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

Text before options labeled (a), (b), (c)

np_acts-logits-general · gemini-2.0-flash

multiple choice options `(a)` `(b)` `(c)`

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

__":

-0.75

 autorytatywna

-0.74

 '\\;'

-0.71

 surla

-0.68

majánló

-0.68

 tartalomajánló

-0.68

expandindo

-0.66

 InputDecoration

-0.65

 iconLine

-0.64

 الحره

-0.63

POSITIVE LOGITS

 defaultstate

0.41

 koron

0.27

TypedValue

0.27

 habet

0.26

достатки

0.26

0.24

 comunicaciones

0.24

 langer

0.24

SneakyThrows

0.24

 among

0.23

Activations Density 0.531%

mathematical or logical symbols and their placements within a context

Text before options labeled (a), (b), (c)

multiple choice options `(a)` `(b)` `(c)`

No Comments

No Known Activations

mathematical or logical symbols and their placements within a context

Text before options labeled (a), (b), (c)

multiple choice options `(a)` `(b)` `(c)`

No Comments

No Known Activations