INDEX

Explanations

patterns related to data handling or processing syntax

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

Binary data and byte sequences

np_acts-logits-general · gemini-2.0-flash

byte counts and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

RTCK

-0.63

mybatisplus

-0.54

Życiorys

-0.54

AsUp

-0.53

Rhestr

-0.52

 igång

-0.50

 queſta

-0.50

Crossref

-0.50

citenamefont

-0.49

initializeApp

-0.49

POSITIVE LOGITS

SerializedSize

0.43

 dAtA

0.39

 oprot

0.35

CodedInputStream

0.35

hoeddwyd

0.34

arraycopy

0.34

Varint

0.34

GetBytes

0.34

bytes

0.33

ByteBuffer

0.33

Activations Density 1.791%

patterns related to data handling or processing syntax

Binary data and byte sequences

byte counts and data structures

No Comments

No Known Activations