INDEX

Explanations

programmatic commands and definitions related to data manipulation and processing within a coding context

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

Code, SQL, configurations, and similar technical expressions

np_acts-logits-general · gemini-2.0-flash

code, technical, and experimental terms

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

or

-0.64

-0.62

in

-0.53

/\.

-0.50

-0.49

-0.48

on

-0.48

-0.47

IContainer

-0.47

-0.46

POSITIVE LOGITS

 myſelf

1.23

 pleaſure

1.21

ConstraintMaker

1.14

 purpoſe

1.09

 itſelf

1.08

 cauſe

1.08

Efq

1.06

 Theſe

1.06

 reaſon

1.05

 raiſ

1.02

Activations Density 0.801%

programmatic commands and definitions related to data manipulation and processing within a coding context

Code, SQL, configurations, and similar technical expressions

code, technical, and experimental terms

No Comments

No Known Activations