INDEX

Explanations

specific numerical and structural references in data-related contexts

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

Acronyms starting with "S"

np_acts-logits-general · gemini-2.0-flash

starts with S

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 برانيه

-0.66

 <=",

-0.59

Personensuche

-0.55

 lccn

-0.53

NewReader

-0.49

contentLoaded

-0.48

 nakalista

-0.47

})));

-0.46

lccn

-0.46

ⓧ

-0.46

POSITIVE LOGITS

1.26

SB

1.10

1.06

SS

1.01

SR

1.00

SJ

0.99

SN

0.99

SG

0.98

SM

0.98

SV

0.96

Activations Density 3.239%

specific numerical and structural references in data-related contexts

Acronyms starting with "S"

starts with S

No Comments

No Known Activations