INDEX

Explanations

mathematical symbols and formatting notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

piecze

-0.52

 strán

-0.47

bibinfo

-0.47

tish

-0.46

Rho

-0.46

iate

-0.45

 vertical

-0.44

 ketahui

-0.44

roj

-0.42

Chất

-0.42

POSITIVE LOGITS

########.

1.18

Personendaten

1.03

mybatisplus

0.97

bootstrapcdn

0.96

 defaultstate

0.93

 NSCoder

0.87

 EconPapers

0.87

verwijspagina

0.87

 Waray

0.86

Xna

0.84

Activations Density 0.806%

mathematical symbols and formatting notations

No Comments

No Known Activations