INDEX

Explanations

technical terms related to signal processing and circuitry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 propOrder

-0.57

WritableDatabase

-0.56

DataContract

-0.54

contentLoaded

-0.51

WIRE

-0.49

ModelSerializer

-0.48

ElementException

-0.47

ospels

-0.47

dersfield

-0.47

 StringTokenizer

-0.46

POSITIVE LOGITS

 processing

0.82

 Processing

0.74

 filtering

0.74

processing

0.72

Processing

0.71

جوايز

0.66

 filtre

0.66

 Filtering

0.66

 Filters

0.66

PROCESSING

0.65

Activations Density 1.141%

technical terms related to signal processing and circuitry

No Comments

No Known Activations