INDEX

Explanations

various numerical values or statistics related to performance metrics and memory operations

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

HTML attribute values

np_acts-logits-general · gemini-2.0-flash

attribute values

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

########.

-0.84

 '\\;'

-0.60

plish

-0.59

 cappello

-0.59

hskip

-0.58

 Rory

-0.57

';

-0.57

Rory

-0.56

Pen

-0.56

]';

-0.56

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.96

 defaultstate

0.90

 snippetHide

0.85

ValueStyle

0.78

 autorytatywna

0.78

 ExecuteAsync

0.77

Autoritní

0.74

abestanden

0.71

Bronnen

0.69

VIAF

0.69

Activations Density 0.006%

various numerical values or statistics related to performance metrics and memory operations

HTML attribute values

attribute values

No Comments

No Known Activations