INDEX

Explanations

keywords related to data handling and class definitions in programming

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

Deals with bytes or binary data

np_acts-logits-general · gemini-2.0-flash

byte data

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

 Clark

-0.48

himu

-0.48

 Rein

-0.44

禅

-0.42

EXPR

-0.41

anat

-0.41

Clark

-0.40

RTLI

-0.40

 pájaros

-0.40

onoi

-0.40

POSITIVE LOGITS

 byte

1.40

byte

1.32

 bytes

1.23

 Byte

1.10

Byte

1.07

bytes

1.05

 Bytes

1.05

Bytes

1.04

字节

0.94

ByteArray

0.89

Activations Density 0.999%

keywords related to data handling and class definitions in programming

Deals with bytes or binary data

byte data

No Comments

No Known Activations