INDEX

Explanations

technical terms related to computer instructions and memory operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

parsedMessage

-0.85

-0.72

 препратки

-0.72

 '\\;'

-0.72

তথ্যসূত্র

-0.68

 ujednoznacz

-0.67

 ProtoMessage

-0.66

AutoScaleMode

-0.65

!*\

-0.63

MemoryWarning

-0.62

POSITIVE LOGITS

 register

0.61

 registre

0.60

 Register

0.59

Register

0.58

register

0.58

 carry

0.53

REGISTER

0.53

 regist

0.53

 registers

0.52

 carrying

0.52

Activations Density 0.315%

technical terms related to computer instructions and memory operations

No Comments

No Known Activations