INDEX

Explanations

keywords related to encoding and data processing in programming

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

Base64 encoding and byte arrays

np_acts-logits-general · gemini-2.0-flash

byte, Bytes, base64 encoding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 âge

-0.52

SharedCtor

-0.49

áh

-0.47

elang

-0.47

sertation

-0.44

rierten

-0.43

PrintWriter

-0.41

plu

-0.41

utrients

-0.41

omination

-0.40

POSITIVE LOGITS

byte

1.05

 byte

0.96

 الحره

0.90

 Bytes

0.88

NSData

0.87

 bytes

0.87

bytes

0.81

Bytes

0.78

ByteString

0.78

 Byte

0.78

Activations Density 0.234%

keywords related to encoding and data processing in programming

Base64 encoding and byte arrays

byte, Bytes, base64 encoding

No Comments

No Known Activations